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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific names or titles

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific names or entities, particularly related to a particular individual or subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pus
    -0.65
     condem
    -0.62
     guiActiveUnfocused
    -0.61
    İĭ
    -0.61
     caucuses
    -0.60
     paraly
    -0.60
     cruc
    -0.60
     opposed
    -0.59
     envy
    -0.59
    wcs
    -0.58
    POSITIVE LOGITS
    renheit
    1.14
    ruary
    1.09
    owship
    0.93
    gerald
    0.92
    ancial
    0.89
    cking
    0.84
    heit
    0.81
    ilon
    0.77
    imore
    0.77
    bah
    0.75
    Act Density 0.136%

    No Known Activations