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

    Neuronpedia

    INDEX
    Explanations

    quotes or expressions followed by a phrase expressing an opinion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the act of quoting or stating opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hift
    -0.77
    ppa
    -0.73
    IELD
    -0.66
    OUND
    -0.64
     Flavoring
    -0.62
    AAA
    -0.61
    ept
    -0.59
     Explosion
    -0.59
     Insect
    -0.58
    inite
    -0.56
    POSITIVE LOGITS
     bluntly
    0.94
    self
    0.84
     succinct
    0.81
     sarcast
    0.76
    chy
    0.69
    unes
    0.68
    alian
    0.66
    selves
    0.66
    zb
    0.65
    MpServer
    0.65
    Act Density 0.052%

    No Known Activations