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

    Neuronpedia

    INDEX
    Explanations

    words related to observations and experimental procedures in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    e
    -0.60
    es
    -0.56
     tilf
    -0.49
     méri
    -0.49
     worthwhile
    -0.47
     samarbe
    -0.47
     statunit
    -0.46
     grises
    -0.45
    midler
    -0.45
     omge
    -0.45
    POSITIVE LOGITS
     isol
    0.78
     celebr
    0.77
     separ
    0.77
     Anim
    0.76
     anim
    0.74
    degrad
    0.73
    Explor
    0.71
     observ
    0.71
     Combin
    0.70
     integr
    0.69
    Act Density 0.553%

    No Known Activations