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

    Neuronpedia

    INDEX
    Explanations

    references to structural models and types in scientific or technical contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.93
     myſelf
    -0.81
    Datuak
    -0.81
     himſelf
    -0.80
     ſtate
    -0.77
     raiſ
    -0.77
     itſelf
    -0.75
     themſelves
    -0.74
     diſt
    -0.74
     houſe
    -0.74
    POSITIVE LOGITS
    Inflater
    0.56
    raszam
    0.55
    }{*}{
    0.54
    :]:
    0.53
    tonsoft
    0.52
     Exacts
    0.51
    ########.
    0.51
    }\]
    0.51
    Eloquent
    0.50
    asmussen
    0.50
    Act Density 0.001%

    No Known Activations