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

    Neuronpedia

    INDEX
    Explanations

    words related to movement or progress

    oai_token-act-pair · gpt-3.5-turbo

    words related to forceful movement or advancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nect
    -0.71
    scl
    -0.64
     Intent
    -0.64
    uden
    -0.63
     descript
    -0.62
    bie
    -0.62
    Trust
    -0.61
    uben
    -0.61
    eon
    -0.59
     toile
    -0.58
    POSITIVE LOGITS
     upward
    0.89
     away
    0.84
     aside
    0.83
     upwards
    0.82
    entious
    0.77
     into
    0.76
     toward
    0.75
     onward
    0.73
     downward
    0.72
     forward
    0.72
    Act Density 0.159%

    No Known Activations