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

    Neuronpedia

    INDEX
    Explanations

    expressions related to taking things for granted

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bef
    -0.15
    BuilderFactory
    -0.14
    raw
    -0.14
    곡
    -0.14
    ÄĻd
    -0.14
    RC
    -0.14
    rc
    -0.14
    üz
    -0.14
     RC
    -0.14
    ãĤ»ãĥ³ãĤ¿ãĥ¼
    -0.14
    POSITIVE LOGITS
     assumed
    0.22
     assumption
    0.21
     assumptions
    0.20
     assume
    0.19
     assumes
    0.17
     assum
    0.17
    /background
    0.16
    assume
    0.16
     prive
    0.15
    368
    0.15
    Act Density 0.063%

    No Known Activations