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

    Neuronpedia

    INDEX
    Explanations

    phrases related to alignment or agreement

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to alignment or coordination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilk
    -0.80
    loo
    -0.75
    HAEL
    -0.71
    oho
    -0.67
    sein
    -0.65
    perty
    -0.64
    bara
    -0.63
    ascus
    -0.63
    ek
    -0.60
    hell
    -0.60
    POSITIVE LOGITS
    ments
    1.36
    iances
    1.02
    arity
    0.96
    eering
    0.93
    ment
    0.91
    icut
    0.87
    pointers
    0.81
    mentation
    0.77
    ations
    0.76
     alignment
    0.75
    Act Density 0.037%

    No Known Activations