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

    Neuronpedia

    INDEX
    Explanations

    expressions of communication and reporting in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    claimer
    -0.16
    arius
    -0.15
    oce
    -0.15
    üss
    -0.15
    ãĥĸãĥª
    -0.15
    stown
    -0.14
    elon
    -0.14
    omatic
    -0.14
    pons
    -0.14
    vertices
    -0.14
    POSITIVE LOGITS
    .sleep
    0.14
     provisioning
    0.14
    asso
    0.14
    TI
    0.13
    989
    0.13
     kles
    0.13
     Recorder
    0.13
    inati
    0.13
    86
    0.13
     sleeper
    0.13
    Act Density 0.160%

    No Known Activations