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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or necessity

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating future or conditional actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.72
    ands
    -0.63
    represented
    -0.61
    vati
    -0.61
    icons
    -0.60
    package
    -0.60
    appings
    -0.59
    IDS
    -0.58
    tracking
    -0.58
    ollar
    -0.58
    POSITIVE LOGITS
     beh
    1.22
     raining
    1.10
     dawn
    0.98
     happen
    0.97
     transpired
    0.92
     matter
    0.86
     rains
    0.82
     cost
    0.82
     seem
    0.78
    iner
    0.77
    Act Density 0.218%

    No Known Activations