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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial or quantitative changes and total figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     recess
    -0.76
     sweat
    -0.66
     persists
    -0.63
     persisted
    -0.62
     Flavoring
    -0.62
     sometimes
    -0.61
     bug
    -0.60
     mischief
    -0.59
    uristic
    -0.59
     flour
    -0.59
    POSITIVE LOGITS
    arthed
    0.96
    senal
    0.80
    arnaev
    0.78
    estone
    0.77
    edIn
    0.75
    ENTS
    0.74
    lege
    0.73
    interstitial
    0.73
    lehem
    0.72
    phabet
    0.72
    Act Density 1.107%

    No Known Activations