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

    Neuronpedia

    INDEX
    Explanations

    mentions of skiing or ski-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to skiing and ski-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ication
    -0.76
    orate
    -0.72
    icating
    -0.69
    ector
    -0.68
    NESS
    -0.68
    eous
    -0.68
    icate
    -0.67
    aneously
    -0.65
    upon
    -0.65
    enance
    -0.65
    POSITIVE LOGITS
     ski
    1.14
     skiing
    1.10
     slope
    0.92
     Ski
    0.91
     slopes
    0.91
    lift
    0.86
     resorts
    0.85
     rink
    0.81
     touring
    0.80
    otin
    0.79
    Act Density 0.008%

    No Known Activations