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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating choices or alternatives

    oai_token-act-pair · gpt-3.5-turbo

    the word "just" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    der
    -0.66
     PLUS
    -0.65
     Palestin
    -0.65
    ccording
    -0.62
     challeng
    -0.61
     Included
    -0.59
     Prelude
    -0.58
     Mushroom
    -0.58
     Documentation
    -0.58
     holiest
    -0.57
    POSITIVE LOGITS
    ifiable
    1.25
    ifications
    1.08
    ifi
    0.96
    if
    0.96
    ified
    0.94
    ices
    0.88
    ification
    0.85
    ifiers
    0.85
     plain
    0.84
    icia
    0.82
    Act Density 0.093%

    No Known Activations