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

    Neuronpedia

    INDEX
    Explanations

    certain verbs and expressions indicating ability, existence, and conditions related to actions or possessive states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oad
    -0.17
    ione
    -0.17
     respectively
    -0.16
    ÐĦ
    -0.15
    esan
    -0.15
     themselves
    -0.14
     respective
    -0.14
    ª½
    -0.14
    ëł¤ê³ł
    -0.14
     Stars
    -0.14
    POSITIVE LOGITS
    embros
    0.20
    reu
    0.18
    yles
    0.17
    Ìĥ
    0.16
    egers
    0.16
    YLES
    0.16
    åĢij
    0.16
    ectors
    0.15
    ypes
    0.15
    ivals
    0.15
    Act Density 0.370%

    No Known Activations