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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progress or development

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to time and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaugh
    -0.82
     destro
    -0.64
     prest
    -0.61
     [*
    -0.60
     Seym
    -0.60
     vulner
    -0.60
    avorite
    -0.59
     advoc
    -0.58
     shenan
    -0.58
    emale
    -0.58
    POSITIVE LOGITS
    Ĥİ
    0.65
    \":
    0.64
    ':
    0.61
     largeDownload
    0.59
    erity
    0.54
    ihad
    0.54
    IGHTS
    0.53
    hillary
    0.51
    cigarettes
    0.50
     Xperia
    0.50
    Act Density 0.731%

    No Known Activations