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

    Neuronpedia

    INDEX
    Explanations

    phrases related to agreeing or moving forward with a course of action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "along" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ns
    -0.74
    inity
    -0.72
    ilies
    -0.70
    iens
    -0.68
    gart
    -0.68
     laun
    -0.68
    inction
    -0.66
    ongyang
    -0.66
    ilities
    -0.65
    ij士
    -0.64
    POSITIVE LOGITS
    side
    0.78
     stairs
    0.76
     nicely
    0.74
    wagon
    0.72
    leys
    0.72
    ments
    0.69
    iously
    0.67
     side
    0.67
    ities
    0.66
     with
    0.65
    Act Density 0.019%

    No Known Activations