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

    Neuronpedia

    INDEX
    Explanations

    phrases related to degrees of intensity or completeness

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant absence or scarcity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beforehand
    -0.51
     conqu
    -0.50
     consulted
    -0.50
     unsuccessfully
    -0.47
    selves
    -0.47
    swick
    -0.46
    chuk
    -0.45
    enment
    -0.45
     breaches
    -0.44
     Bots
    -0.44
    POSITIVE LOGITS
    veland
    0.51
    pmwiki
    0.48
    olin
    0.47
    undrum
    0.45
     alot
    0.42
     fascinating
    0.42
    llular
    0.41
     thee
    0.41
     hypocrisy
    0.41
    imum
    0.40
    Act Density 1.940%

    No Known Activations