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

    Neuronpedia

    INDEX
    Explanations

    well-connected phrases containing the conjunction "and"

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions used to link multiple subjects or details in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ukong
    -0.83
    Zen
    -0.74
    Lay
    -0.72
    aho
    -0.70
    éŃĶ
    -0.70
     Redux
    -0.67
    hov
    -0.65
     Haku
    -0.65
     Mahjong
    -0.64
     (*
    -0.63
    POSITIVE LOGITS
     logistical
    0.75
     expertise
    0.73
     courtroom
    0.72
     diplomatic
    0.71
     volunteer
    0.71
     diplomacy
    0.70
     supportive
    0.69
     spectator
    0.69
     commentary
    0.69
     pund
    0.69
    Act Density 0.496%

    No Known Activations