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

    Neuronpedia

    INDEX
    Explanations

    reflexive verbs and their associated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avaÅŁ
    -0.17
    adaÅŁ
    -0.16
    Insensitive
    -0.15
    CJK
    -0.15
    _RM
    -0.15
    paged
    -0.15
    enheim
    -0.14
    ÑĪев
    -0.14
    ÐĵÐŀ
    -0.14
    _warnings
    -0.14
    POSITIVE LOGITS
     Coy
    0.15
    223
    0.15
     Men
    0.15
    ama
    0.15
    ÑģÑĤа
    0.15
    770
    0.15
     Sent
    0.15
    379
    0.14
    582
    0.14
     Sat
    0.14
    Act Density 0.046%

    No Known Activations