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

    Neuronpedia

    INDEX
    Explanations

    titles or nicknames given to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    quoted phrases or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tackle
    -0.82
     accomp
    -0.81
     grasp
    -0.81
     buoy
    -0.80
     scale
    -0.79
     fret
    -0.79
     gauge
    -0.78
     percentile
    -0.78
     bounce
    -0.77
     +/-
    -0.77
    POSITIVE LOGITS
    little
    1.59
    the
    1.53
    dark
    1.41
    double
    1.40
    gold
    1.37
    dirty
    1.36
    false
    1.36
    mother
    1.35
    grand
    1.35
    black
    1.35
    Act Density 0.131%

    No Known Activations