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

    Neuronpedia

    INDEX
    Explanations

    future-oriented intentions or commitments expressed in the form of "will" and "I'll" phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aterno
    -0.17
    ÑĪов
    -0.15
    abox
    -0.15
    ayne
    -0.15
     yeter
    -0.14
    ateria
    -0.14
    äft
    -0.14
    emand
    -0.14
     antlr
    -0.14
    emia
    -0.13
    POSITIVE LOGITS
     be
    0.20
     admit
    0.19
     bet
    0.18
    l
    0.17
     miss
    0.17
     leave
    0.17
     spare
    0.17
     bets
    0.17
     reserve
    0.15
    ucose
    0.15
    Act Density 0.062%

    No Known Activations