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

    Neuronpedia

    INDEX
    Explanations

    scientific terminology related to experimental data and analysis

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    fjspx
    -1.28
    ſelf
    -1.20
    ſelves
    -1.20
     myſelf
    -1.20
     itſelf
    -1.20
    rungsseite
    -1.18
     themſelves
    -1.16
     pleaſure
    -1.15
    )*/
    -1.11
     ―――――
    -1.11
    POSITIVE LOGITS
    .
    0.60
     U
    0.52
     +
    0.49
    +
    0.49
     (
    0.48
    -
    0.48
    </strong>
    0.46
    ,
    0.46
    ó
    0.46
     and
    0.46
    Act Density 0.034%

    No Known Activations