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

    Neuronpedia

    INDEX
    Explanations

    phrases related to declarations and statements of intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itsu
    -0.16
    _ctxt
    -0.15
    sterol
    -0.15
    soles
    -0.14
    oren
    -0.14
    frau
    -0.14
    ledon
    -0.14
    eren
    -0.14
    shan
    -0.14
    irl
    -0.14
    POSITIVE LOGITS
    aler
    0.16
     Rip
    0.15
     Ry
    0.14
    aji
    0.13
     Deck
    0.13
     Parkway
    0.13
     rip
    0.13
    APH
    0.13
     Hin
    0.13
    ãĥĥãĥģ
    0.13
    Act Density 0.018%

    No Known Activations