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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sudden increases or bursts in activity or quantity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "surge" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĻĤ
    -0.82
    ij
    -0.81
    ĪĴ
    -0.78
    Ĥ
    -0.75
    ¡
    -0.74
    orate
    -0.74
    tein
    -0.73
    Ł
    -0.71
    nered
    -0.70
    66666666
    -0.69
    POSITIVE LOGITS
     surge
    0.85
    ilight
    0.81
    ulic
    0.80
     surges
    0.75
     tide
    0.72
    stakes
    0.70
    tro
    0.66
     surging
    0.66
    ulse
    0.65
    Force
    0.65
    Act Density 0.040%

    No Known Activations