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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "cut," indicating a focus on cutting or related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enta
    -0.16
    oles
    -0.16
    cko
    -0.15
    oi
    -0.15
    eca
    -0.15
    ity
    -0.15
    istor
    -0.14
     Hanna
    -0.14
    annes
    -0.14
    ouns
    -0.13
    POSITIVE LOGITS
    aneous
    0.25
    rippling
    0.20
    0.19
    ãĤ¥
    0.19
    cut
    0.18
    ting
    0.17
    rell
    0.17
    -cut
    0.17
    =cut
    0.17
    throat
    0.17
    Act Density 0.022%

    No Known Activations