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

    Neuronpedia

    INDEX
    Explanations

    prepositions and temporal phrases that indicate specific time frames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.58
     houſe
    -0.54
     itſelf
    -0.53
     CGA
    -0.53
     Vichy
    -0.53
     himſelf
    -0.52
    Grady
    -0.52
     NCS
    -0.52
     Sopho
    -0.50
     Euripides
    -0.50
    POSITIVE LOGITS
     the
    1.12
     their
    0.86
     various
    0.81
    phazard
    0.80
     its
    0.79
    wixt
    0.79
     تانيه
    0.78
    اریخ
    0.77
     a
    0.76
    }}^{(
    0.74
    Act Density 0.476%

    No Known Activations