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

    Neuronpedia

    INDEX
    Explanations

    terms related to user management and online collaboration

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.49
     vicin
    -0.45
    ,
    -0.45
     pre
    -0.43
    過ごす
    -0.43
     i
    -0.42
    \|\
    -0.41
     I
    -0.41
    -
    -0.40
    '
    -0.40
    POSITIVE LOGITS
     ſche
    0.74
     tartalomajánló
    0.73
    parsedMessage
    0.71
     faſt
    0.71
     auffi
    0.70
    ########.
    0.69
    Anhalt
    0.68
    /−
    0.66
     iſt
    0.66
     ſy
    0.66
    Act Density 0.114%

    No Known Activations