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

    Neuronpedia

    INDEX
    Explanations

    words related to tools and equipment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of modification or alteration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    audi
    -0.66
    -0.60
    �
    -0.58
    rus
    -0.51
    bole
    -0.51
    uador
    -0.50
     Silver
    -0.50
    enta
    -0.49
     âĢİ
    -0.49
     Prospect
    -0.48
    POSITIVE LOGITS
     Palest
    0.63
     KE
    0.59
    pload
    0.58
     redes
    0.56
     Khal
    0.49
     condem
    0.49
     destro
    0.49
     Hera
    0.48
    ij士
    0.48
     conclud
    0.47
    Act Density 1.968%

    No Known Activations