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

    Neuronpedia

    INDEX
    Explanations

    references to social interactions and outings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indeed
    -0.16
    rous
    -0.16
    reeze
    -0.16
    eldorf
    -0.15
    _SUITE
    -0.15
     Brush
    -0.15
    raj
    -0.15
    ilver
    -0.14
    ilst
    -0.14
    conds
    -0.14
    POSITIVE LOGITS
    они
    0.15
    ekl
    0.15
    ither
    0.14
    644
    0.14
    ìŀIJëıĻ
    0.14
    nett
    0.14
     seedu
    0.14
    λÏĮ
    0.13
    ECTOR
    0.13
    iye
    0.13
    Act Density 0.197%

    No Known Activations