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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating confusion or uncertainty about a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atsu
    -0.19
    ÑĦекÑĤив
    -0.15
    795
    -0.14
    cona
    -0.14
    Insn
    -0.14
    æ¬
    -0.14
    coe
    -0.14
    .Transactional
    -0.14
    orget
    -0.14
     Belmont
    -0.14
    POSITIVE LOGITS
     tol
    0.16
     guy
    0.15
    eid
    0.14
     âĨĵ
    0.14
    astically
    0.14
    -basic
    0.14
    thouse
    0.14
    wig
    0.14
     basically
    0.14
    enser
    0.14
    Act Density 0.087%

    No Known Activations