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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, such as names and brands

    oai_token-act-pair · gpt-3.5-turbo

    specific brand or product names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     âĵĺ
    -0.82
     Leilan
    -0.81
    £ı
    -0.77
    etheless
    -0.74
    ģĸ
    -0.72
    )=(
    -0.67
     Vald
    -0.65
     forestry
    -0.63
     dispatch
    -0.63
     DISTR
    -0.63
    POSITIVE LOGITS
    ussian
    0.94
    uggle
    0.85
    ollywood
    0.83
    agra
    0.83
    zac
    0.80
    OOOO
    0.78
    akespe
    0.76
    andon
    0.76
    Ps
    0.76
    appy
    0.75
    Act Density 0.535%

    No Known Activations