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

    Neuronpedia

    INDEX
    Explanations

    expressions related to asking for information and conveying knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.57
    ցված
    -0.56
     ComVisible
    -0.50
    AndEndTag
    -0.49
    UnusedPrivate
    -0.48
     tartalomajánló
    -0.47
    owymi
    -0.47
    ysł
    -0.45
    gero
    -0.45
     tal
    -0.44
    POSITIVE LOGITS
     nothing
    1.44
     everything
    1.28
    nothing
    1.27
     anything
    1.24
    Nothing
    1.18
    everything
    1.15
     NOTHING
    1.14
     EVERYTHING
    1.12
     Nothing
    1.09
     something
    1.06
    Act Density 0.229%

    No Known Activations