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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or official matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating evaluations or considerations related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.80
     helicop
    -0.75
    egg
    -0.73
     tatt
    -0.66
     Sieg
    -0.66
     Pengu
    -0.66
     Huck
    -0.65
     submar
    -0.65
     Straw
    -0.64
     suspic
    -0.63
    POSITIVE LOGITS
    unia
    0.82
    ments
    0.81
    eous
    0.81
    ardless
    0.76
    range
    0.75
    ertain
    0.73
    rection
    0.72
     regards
    0.72
    equality
    0.71
    ibility
    0.71
    Act Density 0.031%

    No Known Activations