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

    Neuronpedia

    INDEX
    Explanations

    references to types of "cuts" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALTH
    -0.15
    θε
    -0.15
     Chapman
    -0.14
    ापन
    -0.14
    cks
    -0.14
    оÑĤоÑĢ
    -0.14
    fir
    -0.14
    ium
    -0.14
    halt
    -0.13
    086
    -0.13
    POSITIVE LOGITS
    aneous
    0.17
    0.16
    rell
    0.16
    óc
    0.16
    icle
    0.14
    ®
    0.14
    adel
    0.14
    ÑĢак
    0.14
    omor
    0.14
    YPES
    0.14
    Act Density 0.019%

    No Known Activations