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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or relationships between different concepts or parameters

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    homonymie
    -0.58
    contentLoaded
    -0.54
    ValueStyle
    -0.54
     createSlice
    -0.54
    esterday
    -0.53
     TextAlign
    -0.53
    ween
    -0.52
    czną
    -0.50
    }');
    -0.50
    pay
    -0.49
    POSITIVE LOGITS
     henvisninger
    0.56
    исленность
    0.52
    QUER
    0.51
     onOptions
    0.50
    SharedCtor
    0.50
    Eksterne
    0.50
    bootstrapcdn
    0.50
    alea
    0.47
    quic
    0.46
    ESSION
    0.46
    Act Density 0.107%

    No Known Activations