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

    Neuronpedia

    INDEX
    Explanations

    references to survey respondents and their behaviors or characteristics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    TagMode
    -0.57
     fal
    -0.56
     mergeFrom
    -0.52
    ="@+
    -0.48
    hopefully
    -0.46
    pubsub
    -0.44
     hoped
    -0.43
     hopefully
    -0.43
    mnar
    -0.42
    blogspot
    -0.42
    POSITIVE LOGITS
     &___
    0.69
    AxisAlignment
    0.67
     unsc
    0.66
    +#+#
    0.65
    OrNil
    0.65
     counters
    0.65
    IntoConstraints
    0.64
    InSection
    0.63
    writeFieldEnd
    0.61
     victor
    0.60
    Act Density 0.645%

    No Known Activations