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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and logical relations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تانيه
    -0.82
    wnętr
    -0.81
    rrggbb
    -0.73
     ftate
    -0.69
     Cæsar
    -0.69
     yawn
    -0.69
    Tazama
    -0.69
     reaſon
    -0.67
     habet
    -0.67
     snorkel
    -0.67
    POSITIVE LOGITS
    izing
    0.73
    ating
    0.72
     making
    0.69
     taking
    0.69
     getting
    0.67
     transporting
    0.66
     doing
    0.66
    ting
    0.65
     enjoying
    0.64
     applying
    0.63
    Act Density 0.518%

    No Known Activations