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

    Neuronpedia

    INDEX
    Explanations

    descriptions of conditions or qualities related to objects, people, or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    timewa
    -0.67
    可惜
    -0.51
     smoother
    -0.49
    InputTagHelper
    -0.48
    omeness
    -0.47
     recommandée
    -0.46
     Ruhe
    -0.46
    lrrrr
    -0.45
    stances
    -0.45
    HttpEntity
    -0.45
    POSITIVE LOGITS
     poor
    0.96
    poor
    0.94
    Poor
    0.88
     cheap
    0.83
     Poor
    0.82
     POOR
    0.81
     poorest
    0.79
    Cheap
    0.78
     rudimentary
    0.78
     cheaply
    0.77
    Act Density 0.551%

    No Known Activations