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

    Neuronpedia

    INDEX
    Explanations

    words related to the physical description or characteristics of something

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usalem
    -0.70
    awaru
    -0.68
    etus
    -0.67
     sacked
    -0.65
    aea
    -0.64
    LM
    -0.62
    JJ
    -0.62
    hett
    -0.59
    ueller
    -0.58
    escal
    -0.58
    POSITIVE LOGITS
    enough
    0.72
    geries
    0.69
    clusions
    0.65
     bordering
    0.63
     Roose
    0.61
     Mystic
    0.60
     Carth
    0.60
     Subtle
    0.57
    poly
    0.57
    oxide
    0.56
    Act Density 0.540%

    No Known Activations