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

    Neuronpedia

    INDEX
    Explanations

    the presence and variety of existential phrases and quantifiers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ריכה
    -0.56
    newline
    -0.49
    oluzione
    -0.48
    flink
    -0.48
     cause
    -0.47
     dis
    -0.47
     '
    -0.46
    SPJ
    -0.46
     "
    -0.46
    alnya
    -0.45
    POSITIVE LOGITS
    AndEndTag
    0.89
     tranſ
    0.76
     îna
    0.75
     Charlemagne
    0.75
     незавершена
    0.73
     cammino
    0.71
     centrality
    0.69
     تضيفلها
    0.69
     poffible
    0.69
     ſta
    0.69
    Act Density 0.041%

    No Known Activations