Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    action-oriented phrases related to processes and participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words and phrases describing the ability or capacity to perform actions or tasks.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    slightly
    -0.44
     ujednoznacz
    -0.42
    GenerationType
    -0.42
    Notae
    -0.40
    numerusform
    -0.40
    contentLoaded
    -0.39
    енча
    -0.39
    Personendaten
    -0.39
     externi
    -0.39
     Gelegenheit
    -0.38
    POSITIVE LOGITS
     successfully
    1.90
     safely
    1.73
     efficiently
    1.72
     correctly
    1.66
     satisfactorily
    1.61
     successful
    1.61
     Successfully
    1.55
     effectively
    1.55
     properly
    1.53
    successfully
    1.52
    Act Density 1.255%

    No Known Activations