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

    Neuronpedia

    INDEX
    Explanations

    phrases related to checking off items or completing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ool
    -0.15
    žÃŃ
    -0.14
    sip
    -0.14
    zd
    -0.14
    dra
    -0.14
    adier
    -0.14
    ekil
    -0.14
    eing
    -0.13
    rats
    -0.13
    ÏĨÏħ
    -0.13
    POSITIVE LOGITS
    alin
    0.16
    ulumi
    0.16
    bris
    0.15
     reck
    0.15
     OnDestroy
    0.15
    essen
    0.14
    ahoma
    0.14
     Mech
    0.14
    ordon
    0.14
     removeObject
    0.14
    Act Density 0.036%

    No Known Activations