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

    Neuronpedia

    INDEX
    Explanations

    references to official events and gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĢĨ
    -0.16
    umor
    -0.16
    ilar
    -0.16
    è®
    -0.15
    ateria
    -0.15
    activex
    -0.15
    bens
    -0.15
     attendee
    -0.14
    _PENDING
    -0.14
    erver
    -0.14
    POSITIVE LOGITS
     press
    0.23
     forum
    0.22
     signing
    0.21
     closing
    0.20
     meeting
    0.20
     pl
    0.19
     launching
    0.19
     sym
    0.19
     launch
    0.19
     swearing
    0.19
    Act Density 0.173%

    No Known Activations