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

    Neuronpedia

    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    the name "Tim" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reloaded
    -0.69
     pleas
    -0.61
    Magikarp
    -0.58
     prolifer
    -0.58
    ATS
    -0.57
     lessons
    -0.57
     criminally
    -0.56
     Letters
    -0.55
     resid
    -0.55
     fractions
    -0.55
    POSITIVE LOGITS
    othy
    1.28
    eless
    1.26
    estamp
    1.25
    elines
    1.11
    oleon
    1.09
     Hort
    1.08
    mons
    1.05
    my
    1.04
    eline
    1.03
    oshenko
    1.01
    Act Density 0.027%

    No Known Activations