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

    Neuronpedia

    INDEX
    Explanations

    words describing emotional and physical experiences

    oai_token-act-pair · gemini-2.0-flash

    liked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -1.24
     Monfieur
    -1.13
     pleaſure
    -1.13
     houſe
    -1.13
     Eſ
    -1.10
     purpoſe
    -1.09
     myſelf
    -1.05
     itſelf
    -1.04
     himſelf
    -1.02
    vellous
    -0.97
    POSITIVE LOGITS
    <bos>
    0.68
    ,
    0.61
    -
    0.53
    ộn
    0.52
    L
    0.51
    <i>
    0.47
    .
    0.47
     can
    0.46
    a
    0.45
    --
    0.44
    Act Density 1.229%

    No Known Activations