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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to scientific measurements or parameters

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     poffe
    -1.09
     preſent
    -1.05
     ſtate
    -1.05
     MainAxisSize
    -1.04
     pleaſure
    -1.03
     purpoſe
    -1.02
    extAlignment
    -1.02
     ſtill
    -1.00
     houſe
    -0.98
     raiſ
    -0.98
    POSITIVE LOGITS
    ,
    0.63
    ↵
    0.57
    .
    0.57
    :
    0.55
    ↵↵
    0.54
     co
    0.52
     —
    0.52
     "
    0.49
     “
    0.49
     (
    0.48
    Act Density 0.025%

    No Known Activations