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

    Neuronpedia

    INDEX
    Explanations

    the word "because" followed by a justification or reasoning

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "just because"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exclusive
    -0.70
    anon
    -0.68
    uv
    -0.66
     Loft
    -0.64
    esi
    -0.63
    TPPStreamerBot
    -0.63
    tnc
    -0.63
    Hu
    -0.62
    Ku
    -0.61
    ufact
    -0.61
    POSITIVE LOGITS
    */(
    0.81
    cause
    0.74
     SOME
    0.68
    insk
    0.68
     somebody
    0.66
    ricular
    0.65
     THEY
    0.64
     someone
    0.63
    hetto
    0.61
    lihood
    0.60
    Act Density 0.027%

    No Known Activations