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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing speculative or counterfactual situations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "would have" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     muse
    -0.63
     rumor
    -0.60
     narrator
    -0.59
     plaintiff
    -0.57
     disinfect
    -0.55
     doll
    -0.54
     Cold
    -0.54
     trope
    -0.54
     reminder
    -0.53
     marqu
    -0.53
    POSITIVE LOGITS
     been
    1.03
     gotten
    0.93
    been
    0.93
    0.89
    ĸļ
    0.89
    Ģ
    0.80
     taken
    0.79
    ãĥ´ãĤ¡
    0.78
     Been
    0.78
    gotten
    0.76
    Act Density 0.076%

    No Known Activations