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

    Neuronpedia

    INDEX
    Explanations

    terms related to individualism and personal identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /he
    -0.17
    upy
    -0.16
    §
    -0.16
    enia
    -0.16
    fait
    -0.15
    atology
    -0.15
    á»ķ
    -0.15
    own
    -0.15
    lix
    -0.14
    _FLOW
    -0.14
    POSITIVE LOGITS
    ized
    0.37
    ised
    0.32
    istic
    0.29
    ity
    0.27
    /group
    0.25
    IZED
    0.25
    /team
    0.23
    ize
    0.22
    swith
    0.20
    izado
    0.20
    Act Density 0.025%

    No Known Activations