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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sources or origins

    oai_token-act-pair · gpt-3.5-turbo

    references to the source of various media or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bably
    -0.83
    merce
    -0.81
    mun
    -0.80
    pose
    -0.80
    perty
    -0.79
    ratulations
    -0.77
    mere
    -0.72
    few
    -0.71
    opausal
    -0.70
    vacc
    -0.69
    POSITIVE LOGITS
     afar
    1.37
     whence
    0.89
     anywhere
    0.83
     inside
    0.82
     antiquity
    0.77
     scratch
    0.74
     nowhere
    0.73
     underneath
    0.72
     scrimmage
    0.72
     abroad
    0.72
    Act Density 0.132%

    No Known Activations