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

    Neuronpedia

    INDEX
    Explanations

    companion terms or descriptors referring to a main subject or concept

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.66
    UGE
    -0.66
    uman
    -0.65
    mberg
    -0.60
    ball
    -0.59
    ihil
    -0.56
    uda
    -0.55
    uge
    -0.54
     phosph
    -0.54
    ulic
    -0.53
    POSITIVE LOGITS
     companions
    0.90
    hip
    0.84
     companion
    0.84
     Companion
    0.80
    lihood
    0.73
    finder
    0.67
    hesis
    0.66
     Compan
    0.65
    piece
    0.63
    ively
    0.62
    Act Density 6.789%

    No Known Activations