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

    Neuronpedia

    INDEX
    Explanations

    words related to specific political figures and locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "ICH" and related identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beetle
    -0.72
    brance
    -0.70
    backer
    -0.69
    asonable
    -0.66
    behavior
    -0.65
     plural
    -0.64
    pillar
    -0.62
     Spiral
    -0.62
     Glob
    -0.62
    icable
    -0.62
    POSITIVE LOGITS
    ICH
    1.18
    ARD
    1.11
    ARDS
    0.99
    INA
    0.86
    OUGH
    0.86
    HAEL
    0.85
    ards
    0.81
    OME
    0.81
    NESS
    0.80
    IGH
    0.79
    Act Density 0.003%

    No Known Activations