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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.87
    vez
    -0.79
     pige
    -0.63
    FTWARE
    -0.63
     flux
    -0.62
     Tanz
    -0.60
     Galile
    -0.60
     mosa
    -0.59
     contrace
    -0.59
     Roses
    -0.58
    POSITIVE LOGITS
    ornia
    1.31
    amily
    1.04
    ield
    0.99
    orce
    0.97
    rame
    0.89
    ascist
    0.87
    ieth
    0.86
    rag
    0.85
    riend
    0.85
    aces
    0.85
    Act Density 0.006%

    No Known Activations