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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    words related to birds and their various characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cheong
    -0.67
     jurors
    -0.60
    CLASS
    -0.57
     Kov
    -0.55
     PJ
    -0.55
     gram
    -0.55
     subpoena
    -0.55
    dk
    -0.54
     occasion
    -0.54
     prop
    -0.54
    POSITIVE LOGITS
    ulhu
    0.86
    abre
    0.80
    ãĤ¼ãĤ¦ãĤ¹
    0.75
    rera
    0.73
    pillar
    0.73
    estine
    0.72
    berus
    0.71
    é¾įåĸļ士
    0.69
    nect
    0.68
    rency
    0.68
    Act Density 0.102%

    No Known Activations