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

    Neuronpedia

    INDEX
    Explanations

    instances of temporal expressions indicating anticipation or events that are expected to happen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -1.07
    Ħ¢
    -0.82
    ãĤ´ãĥ³
    -0.81
    cffffcc
    -0.79
    SourceFile
    -0.76
    soDeliveryDate
    -0.74
    ĺ
    -0.73
    veh
    -0.73
    ¸
    -0.73
    Ĥª
    -0.73
    POSITIVE LOGITS
     recovering
    0.89
     exhaustion
    0.85
     needing
    0.80
     somebody
    0.80
     someone
    0.79
     succ
    0.78
     exhausted
    0.74
    alties
    0.74
     encountering
    0.73
     realizes
    0.73
    Act Density 0.231%

    No Known Activations