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

    Neuronpedia

    INDEX
    Explanations

    instances of deception or concealment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elier
    -0.15
    ihan
    -0.15
    uted
    -0.14
    sha
    -0.14
     Haj
    -0.14
    lobe
    -0.14
    terior
    -0.13
     ÏĢε
    -0.13
    cient
    -0.13
    ога
    -0.13
    POSITIVE LOGITS
    _firestore
    0.17
    æİī
    0.17
    ous
    0.16
    eniable
    0.16
    away
    0.16
     hide
    0.16
    isclosed
    0.15
    .opend
    0.15
    ousse
    0.15
     hid
    0.15
    Act Density 0.059%

    No Known Activations