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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases indicating impossibility or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anes
    -0.19
    abi
    -0.15
     ÑģÑĤаÑĢа
    -0.15
    auses
    -0.14
    ýv
    -0.14
    esini
    -0.14
     æ¬
    -0.14
    avs
    -0.14
    apper
    -0.14
    ntax
    -0.13
    POSITIVE LOGITS
     be
    0.26
     anymore
    0.26
     necessarily
    0.25
     able
    0.23
     ever
    0.23
     unless
    0.22
     mind
    0.21
     EVER
    0.20
    -ever
    0.19
     ability
    0.18
    Act Density 0.087%

    No Known Activations