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

    Neuronpedia

    INDEX
    Explanations

    words related to actions or processes that involve creation or development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    setopt
    -1.01
     getRule
    -0.95
     Ruh
    -0.84
    acre
    -0.81
    konomi
    -0.78
     flesta
    -0.76
    ্ন
    -0.73
    جموعة
    -0.73
    issauga
    -0.73
    angeran
    -0.72
    POSITIVE LOGITS
    ting
    1.31
    ating
    1.21
    ning
    1.19
    NING
    1.16
    ging
    1.16
    izing
    1.14
    TING
    1.09
    ING
    1.08
    ming
    1.07
    ling
    1.07
    Act Density 0.633%

    No Known Activations