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

    Neuronpedia

    INDEX
    Explanations

    references to digital data sizes and formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hoort
    -0.51
    ostante
    -0.46
    ConstraintMaker
    -0.45
    tênis
    -0.44
     tätig
    -0.44
     towarzys
    -0.43
     utrzy
    -0.43
     mármol
    -0.42
     mantend
    -0.42
     neemt
    -0.42
    POSITIVE LOGITS
     character
    0.77
     bit
    0.75
     stage
    0.70
    spirit
    0.69
     spirit
    0.67
     Bit
    0.66
     Spirit
    0.65
     STAGE
    0.65
    possession
    0.64
     stages
    0.63
    Act Density 0.178%

    No Known Activations