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

    Neuronpedia

    INDEX
    Explanations

    verbs related to movement and direction

    oai_token-act-pair · gpt-3.5-turbo

    active verbs indicating movement or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aptic
    -0.72
    cert
    -0.68
    reements
    -0.67
     collateral
    -0.66
    urers
    -0.65
    deal
    -0.64
    ĻĤ
    -0.63
    Deal
    -0.61
     corpus
    -0.61
    nect
    -0.59
    POSITIVE LOGITS
     ashore
    0.98
     into
    0.94
     through
    0.84
     across
    0.83
     along
    0.82
     onto
    0.80
    cade
    0.79
     alongside
    0.76
     toward
    0.76
     hither
    0.75
    Act Density 0.160%

    No Known Activations