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

    Neuronpedia

    INDEX
    Explanations

    events or incidents triggering controversy or conflict

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "when" indicating the timing of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agin
    -0.69
    plus
    -0.67
    ãĤ«
    -0.64
    probably
    -0.64
    ax
    -0.64
    bear
    -0.64
    Í
    -0.62
    whatever
    -0.61
    1000
    -0.60
    ãĤ¤ãĥĪ
    -0.59
    POSITIVE LOGITS
    soever
    1.37
     they
    0.78
     confronted
    0.77
     comparing
    0.76
     faced
    0.74
     compared
    0.73
     someone
    0.72
     encountering
    0.71
     pitted
    0.68
     asked
    0.65
    Act Density 0.095%

    No Known Activations