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

    Neuronpedia

    INDEX
    Explanations

    references to a group identity or collective experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĢij
    -0.18
    rim
    -0.16
    wahl
    -0.16
    mar
    -0.16
    ãĥ³ãĥij
    -0.15
    oub
    -0.14
    ne
    -0.14
    mit
    -0.14
    ng
    -0.14
    mq
    -0.14
    POSITIVE LOGITS
    aver
    0.20
    athers
    0.19
    icker
    0.19
    igt
    0.19
    evil
    0.18
    issen
    0.18
    ALTH
    0.18
    ighb
    0.17
    aire
    0.17
    blink
    0.17
    Act Density 0.084%

    No Known Activations