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

    Neuronpedia

    INDEX
    Explanations

    titles and phrases related to academic publications and methodologies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.59
     pageContext
    -0.55
     wireType
    -0.54
     فريبيس
    -0.52
    StructEnd
    -0.51
     Rock
    -0.49
     ddelweddau
    -0.49
    çoit
    -0.47
    SuppressMessage
    -0.47
     transfieras
    -0.47
    POSITIVE LOGITS
    ArgsConstructor
    0.72
    IBOutlet
    0.58
     oignons
    0.57
    OGND
    0.54
     auroit
    0.53
    otient
    0.53
    帖最后由
    0.52
     înal
    0.52
     hänen
    0.52
     relics
    0.51
    Act Density 0.051%

    No Known Activations