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

    Neuronpedia

    INDEX
    Explanations

    expressions of awareness or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alli
    -0.15
    eway
    -0.14
    illis
    -0.14
    oplan
    -0.14
    ViewInit
    -0.14
    atables
    -0.14
    ouch
    -0.14
     wParam
    -0.14
     Darkness
    -0.13
    æķ¦
    -0.13
    POSITIVE LOGITS
    ospace
    0.16
    jom
    0.16
    erap
    0.15
    SEG
    0.14
    edback
    0.14
    uru
    0.14
    msg
    0.14
    Segment
    0.13
     λα
    0.13
    iesen
    0.13
    Act Density 0.001%

    No Known Activations