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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating support or endorsement

    oai_token-act-pair · gpt-3.5-turbo

    references to support or endorsement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ldom
    -0.77
    kay
    -0.76
    hunt
    -0.70
    elsius
    -0.67
    asso
    -0.66
    vent
    -0.66
    breaker
    -0.65
    arcity
    -0.64
    hunter
    -0.64
    ixtape
    -0.64
    POSITIVE LOGITS
     Supported
    0.75
     Supports
    0.74
     Supporting
    0.73
     supporting
    0.71
     supported
    0.69
    byn
    0.69
     corrobor
    0.68
    Support
    0.68
    dash
    0.67
     charities
    0.67
    Act Density 0.034%

    No Known Activations