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

    Neuronpedia

    INDEX
    Explanations

    code-related terms that specify the type of a program or method, particularly focusing on final modifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ioc
    -0.16
    borough
    -0.16
    ious
    -0.16
    emic
    -0.15
    alars
    -0.15
    loquent
    -0.15
     Ä°h
    -0.15
    onse
    -0.14
    hest
    -0.14
    oot
    -0.14
    POSITIVE LOGITS
     wasted
    0.14
    tl
    0.14
    ity
    0.14
    antro
    0.14
    teen
    0.14
     Latter
    0.13
    l
    0.13
     Maher
    0.13
    cial
    0.13
    axter
    0.13
    Act Density 0.006%

    No Known Activations