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

    Neuronpedia

    INDEX
    Explanations

    verbs related to offering support or reinforcement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "back" and related forms indicating support or reinforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itizen
    -0.78
    entric
    -0.70
    alde
    -0.65
    ifix
    -0.62
    thora
    -0.61
     newsp
    -0.60
    olia
    -0.58
     incidentally
    -0.57
     rele
    -0.57
     irony
    -0.56
    POSITIVE LOGITS
    track
    1.26
     away
    1.14
    ped
    1.04
     down
    0.98
     up
    0.82
    tracking
    0.82
     Away
    0.81
    tr
    0.80
     off
    0.78
    stop
    0.76
    Act Density 0.042%

    No Known Activations