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

    Neuronpedia

    INDEX
    Explanations

    references to handles

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    gwick
    -0.87
     $_"
    -0.83
    SBATCH
    -0.77
    =$?
    -0.76
    OrNil
    -0.75
    tanleria
    -0.71
    uanya
    -0.70
    asthan
    -0.70
     devoir
    -0.70
     betweenstory
    -0.69
    POSITIVE LOGITS
    HANDLE
    0.77
     HANDLE
    0.73
     Handle
    0.70
    Handle
    0.65
    handle
    0.64
     McDon
    0.63
     holes
    0.62
     HOLE
    0.62
     estimés
    0.62
    AnchorStyles
    0.61
    Act Density 0.004%

    No Known Activations