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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    oai_token-act-pair · gpt-3.5-turbo

    phrases or clauses indicating uncertainty or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Uganda
    -0.65
     glyphosate
    -0.59
    orer
    -0.59
    reach
    -0.59
     Capitol
    -0.58
     Petersburg
    -0.57
     Hew
    -0.56
     Amph
    -0.55
     Havana
    -0.55
    ower
    -0.55
    POSITIVE LOGITS
     alternatively
    0.98
    Else
    0.93
    acle
    0.82
    abouts
    0.81
    depending
    0.78
    nam
    0.77
    thodox
    0.71
    ught
    0.70
    incarn
    0.69
    rox
    0.67
    Act Density 0.112%

    No Known Activations