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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or phrases indicating conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.85
    âĸ¬
    -0.72
    heimer
    -0.67
    alus
    -0.66
    vez
    -0.66
    holm
    -0.64
    kees
    -0.63
    perse
    -0.63
     Mour
    -0.62
    odore
    -0.62
    POSITIVE LOGITS
    ornia
    1.00
    unction
    0.94
    amily
    0.90
    FER
    0.89
    TY
    0.83
    ICA
    0.82
    FIN
    0.82
    orce
    0.81
    rame
    0.79
    TER
    0.79
    Act Density 0.007%

    No Known Activations