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

    Neuronpedia

    INDEX
    Explanations

    phrases related to support and standing up for others or causes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strar
    -0.17
    osate
    -0.16
    endale
    -0.16
    edad
    -0.16
    ceptive
    -0.16
    icus
    -0.15
    going
    -0.15
    dept
    -0.15
    sein
    -0.14
    endon
    -0.14
    POSITIVE LOGITS
    -alone
    0.23
    rase
    0.16
    ings
    0.15
    Charsets
    0.15
    ARDS
    0.14
    rev
    0.14
    496
    0.14
    -valu
    0.14
    بÛĮر
    0.13
    CLUDING
    0.13
    Act Density 0.046%

    No Known Activations