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

    Neuronpedia

    INDEX
    Explanations

    terms related to providing help or support

    oai_token-act-pair · gpt-3.5-turbo

    mentions of assistance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aval
    -0.80
    steel
    -0.75
    ls
    -0.75
    ross
    -0.73
    bread
    -0.72
    nen
    -0.71
    city
    -0.70
    bish
    -0.70
    Benz
    -0.69
    polit
    -0.68
    POSITIVE LOGITS
     assistance
    0.95
     Assistance
    0.83
     aid
    0.81
    ateral
    0.80
    enza
    0.78
     SERVICES
    0.78
    ":["
    0.74
     recipients
    0.74
     Programs
    0.74
    oice
    0.73
    Act Density 0.019%

    No Known Activations