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

    Neuronpedia

    INDEX
    Explanations

    phrases related to central themes or focuses in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to debates or discussions that revolve around a central topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå
    -0.66
    apes
    -0.63
    antha
    -0.63
    ãĥīãĥ©
    -0.60
    asis
    -0.59
    inx
    -0.58
    apon
    -0.58
    edom
    -0.58
    iddler
    -0.58
    ãģĹ
    -0.57
    POSITIVE LOGITS
     principally
    0.92
    vre
    0.90
    yrinth
    0.88
     solely
    0.86
     primarily
    0.85
    ussed
    0.84
     mainly
    0.84
     exclusively
    0.82
     chiefly
    0.81
    ovie
    0.81
    Act Density 0.108%

    No Known Activations