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

    Neuronpedia

    INDEX
    Explanations

    forms or types related to different concepts or entities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Bullets
    -0.71
     places
    -0.57
     Places
    -0.54
     sacrific
    -0.53
     Parenthood
    -0.53
    ullivan
    -0.53
     limbs
    -0.52
     Associates
    -0.52
     Doors
    -0.51
     Dupl
    -0.51
    POSITIVE LOGITS
     of
    0.92
     thereof
    0.76
    OF
    0.76
    dev
    0.69
    nings
    0.67
    ada
    0.64
    Of
    0.64
     Of
    0.62
    adan
    0.62
    of
    0.61
    Act Density 0.240%

    No Known Activations