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

    Neuronpedia

    INDEX
    Explanations

    conditional statements indicating potential actions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    words related to obligation or expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icular
    -0.68
    oos
    -0.64
    enda
    -0.63
     Peaks
    -0.63
    ongs
    -0.62
    endas
    -0.62
     commod
    -0.61
    acus
    -0.60
    conduct
    -0.60
    eness
    -0.58
    POSITIVE LOGITS
     Hover
    0.72
    terday
    0.70
    tm
    0.65
     November
    0.63
     Sly
    0.63
    terms
    0.62
     regards
    0.61
     Leban
    0.61
    EMBER
    0.61
     Aval
    0.61
    Act Density 0.704%

    No Known Activations