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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "alone" accompanied by contextual information about a person or group

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities that are not alone in their actions or circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imize
    -0.76
    obal
    -0.73
    imate
    -0.73
    bern
    -0.65
    ewater
    -0.64
     respectively
    -0.62
    eer
    -0.62
    achment
    -0.59
    raviolet
    -0.59
    arov
    -0.59
    POSITIVE LOGITS
    ATA
    0.85
    NPR
    0.74
    Compl
    0.71
    WT
    0.71
     traged
    0.70
    ingen
    0.68
     contentious
    0.68
    atche
    0.67
     controversies
    0.67
    è¦ļéĨĴ
    0.66
    Act Density 0.172%

    No Known Activations