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

    Neuronpedia

    INDEX
    Explanations

    journalists who write columns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of columnists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resses
    -0.76
    asonic
    -0.76
    sure
    -0.75
    ramid
    -0.73
    qual
    -0.72
    lace
    -0.72
    smoking
    -0.71
    birth
    -0.71
    alin
    -0.71
    ressing
    -0.70
    POSITIVE LOGITS
     columnist
    1.26
     writer
    0.97
     laureate
    0.96
     editor
    0.83
     contributor
    0.83
     satir
    0.81
    itatively
    0.79
     journalist
    0.78
    oad
    0.78
     blogger
    0.77
    Act Density 0.010%

    No Known Activations