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

    Neuronpedia

    INDEX
    Explanations

    phrases describing compositions or structures

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the composition or structure of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hawks
    -0.67
    ilings
    -0.67
    bury
    -0.65
    Flying
    -0.61
     Karma
    -0.60
    WT
    -0.60
     Taj
    -0.60
     Dull
    -0.58
    fly
    -0.58
    Sil
    -0.58
    POSITIVE LOGITS
     consist
    0.89
    galitarian
    0.87
    ģ«
    0.85
     consisted
    0.81
     comprised
    0.80
     solely
    0.79
     consists
    0.78
    encies
    0.78
    ĸļ
    0.76
    alion
    0.76
    Act Density 0.010%

    No Known Activations