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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "So what" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    questions beginning with "what."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DAQ
    -0.74
    JM
    -0.70
    yers
    -0.68
    Kit
    -0.68
    Bound
    -0.67
    TM
    -0.65
    MER
    -0.65
    eds
    -0.64
    ERG
    -0.63
    KI
    -0.62
    POSITIVE LOGITS
     happens
    0.91
     ensued
    0.88
     else
    0.86
     happened
    0.85
    etheless
    0.85
     transpired
    0.84
     separates
    0.78
     emerges
    0.76
     happ
    0.75
     exactly
    0.73
    Act Density 0.076%

    No Known Activations