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

    Neuronpedia

    INDEX
    Explanations

    phrases related to projects or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    instances of empty or unspecified content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prest
    -0.74
    farious
    -0.69
     seiz
    -0.65
     helicop
    -0.65
    emale
    -0.63
     Gaw
    -0.62
     destro
    -0.60
     territ
    -0.59
     Blossom
    -0.58
    erenn
    -0.56
    POSITIVE LOGITS
     âĸº
    0.62
     ]
    0.62
    lement
    0.59
     ][
    0.57
     Psy
    0.56
    ="#
    0.53
    coins
    0.53
    amins
    0.53
    bands
    0.52
    files
    0.52
    Act Density 0.175%

    No Known Activations