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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences indicating expectations or predictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing expectations or predictions about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.69
    FX
    -0.65
     Sure
    -0.63
     Plain
    -0.63
     Tracks
    -0.62
    Loop
    -0.62
     Primordial
    -0.61
     Connection
    -0.61
    Lear
    -0.61
    pite
    -0.59
    POSITIVE LOGITS
     be
    1.09
     reap
    1.02
     perform
    0.97
     shake
    0.96
     arrive
    0.96
     bring
    0.91
     incorporate
    0.89
     settle
    0.89
     explode
    0.88
     solve
    0.88
    Act Density 0.089%

    No Known Activations