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

    Neuronpedia

    INDEX
    Explanations

    references to self-identification or expressions of personal state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apult
    -0.16
    elerik
    -0.16
    ertools
    -0.15
    lectron
    -0.15
    pend
    -0.15
    auc
    -0.14
    ichel
    -0.13
    uele
    -0.13
    rchive
    -0.13
    ãĤ»ãĥ³
    -0.13
    POSITIVE LOGITS
     using
    0.20
     familiar
    0.19
     sure
    0.19
     new
    0.18
     having
    0.17
    los
    0.17
     fairly
    0.16
    Wonder
    0.16
     able
    0.16
     Using
    0.16
    Act Density 0.064%

    No Known Activations