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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Duncan
    -0.16
    łģ
    -0.15
    uncan
    -0.15
    iji
    -0.15
    okol
    -0.15
     Mellon
    -0.14
     Columbia
    -0.14
     èİ
    -0.14
     Colum
    -0.14
     herk
    -0.14
    POSITIVE LOGITS
    54
    0.36
    74
    0.36
    94
    0.35
    04
    0.34
    14
    0.34
    34
    0.34
    ľ´
    0.32
     Fourth
    0.32
    ç¬¬åĽĽ
    0.32
    84
    0.32
    Act Density 0.108%

    No Known Activations