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

    Neuronpedia

    INDEX
    Explanations

    statements of correctness or agreement

    oai_token-act-pair · gpt-3.5-turbo

    assertions of correctness or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.82
    gins
    -0.78
    ĸļ
    -0.74
     Gong
    -0.70
     Pastebin
    -0.69
    effic
    -0.68
    WAYS
    -0.67
     Remastered
    -0.64
    hens
    -0.63
    ains
    -0.63
    POSITIVE LOGITS
    eous
    0.96
    headed
    0.88
    footed
    0.88
     smack
    0.77
     wing
    0.75
    eyed
    0.75
    fully
    0.73
    terday
    0.71
     fielder
    0.71
    ness
    0.70
    Act Density 0.043%

    No Known Activations