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

    Neuronpedia

    INDEX
    Explanations

    instances of the string "amer"

    oai_token-act-pair · gpt-3.5-turbo

    references to American identities or cultural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ŃĶ
    -0.73
    ĵĺ
    -0.69
    staking
    -0.68
    margin
    -0.66
    Gi
    -0.63
     greenhouse
    -0.61
     hem
    -0.61
     foregoing
    -0.61
     raw
    -0.60
     stocking
    -0.59
    POSITIVE LOGITS
    ican
    1.39
    icans
    1.34
    ICAN
    1.21
    icas
    1.03
    ica
    1.02
    icity
    0.98
    gency
    0.98
    ikan
    0.97
    gdala
    0.94
    agic
    0.94
    Act Density 0.007%

    No Known Activations