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

    Neuronpedia

    INDEX
    Explanations

    instances of words related to control or guidance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to control and guidance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issues
    -0.88
    ouf
    -0.77
    nen
    -0.77
    adra
    -0.73
    osaurs
    -0.73
    older
    -0.71
    sters
    -0.71
    stadt
    -0.69
    ager
    -0.69
    ilk
    -0.68
    POSITIVE LOGITS
     demolition
    0.92
     demol
    0.81
    elta
    0.80
    uction
    0.77
     combustion
    0.72
     clinical
    0.71
    paren
    0.71
    own
    0.71
     Destruction
    0.70
     BY
    0.69
    Act Density 0.198%

    No Known Activations