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

    Neuronpedia

    INDEX
    Explanations

    website features or actions releated to saving/bookmarking content

    oai_token-act-pair · gpt-3.5-turbo

    references to the action of marking or bookmarking items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agan
    -0.73
    bent
    -0.68
     wages
    -0.64
     dancers
    -0.63
     neglig
    -0.62
     dancer
    -0.61
    apist
    -0.61
     waves
    -0.61
     overcome
    -0.61
     bra
    -0.60
    POSITIVE LOGITS
    hyde
    1.04
    tenance
    0.95
    mark
    0.92
    eer
    0.89
    eters
    0.86
    /-
    0.85
    ing
    0.78
    eering
    0.77
    ijk
    0.76
    manship
    0.74
    Act Density 0.030%

    No Known Activations