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

    Neuronpedia

    INDEX
    Explanations

    specific names, terms, or constructs related to scientific and technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shut
    -0.18
     sting
    -0.15
     ple
    -0.15
     Ko
    -0.15
     Studio
    -0.15
     studio
    -0.14
    wers
    -0.14
    ALLE
    -0.14
     Santa
    -0.14
     bott
    -0.14
    POSITIVE LOGITS
     Joseph
    0.29
    Joseph
    0.25
     pairing
    0.25
     super
    0.24
     jose
    0.24
    pair
    0.21
    super
    0.20
    .super
    0.19
     pair
    0.19
     dirty
    0.19
    Act Density 0.001%

    No Known Activations