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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lse
    -0.20
    immers
    -0.15
    angu
    -0.15
    dn
    -0.15
    dent
    -0.14
    rawer
    -0.14
    okoj
    -0.14
    iza
    -0.14
    ENSOR
    -0.13
    dle
    -0.13
    POSITIVE LOGITS
     fun
    0.18
    ató
    0.18
     hire
    0.18
     FUN
    0.17
    sembling
    0.16
    _fun
    0.15
     pleasure
    0.15
    plier
    0.15
    Fun
    0.15
     ============================================================================↵
    0.14
    Act Density 0.101%

    No Known Activations