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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the substring "th" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edback
    -0.18
    oya
    -0.16
    롱
    -0.16
    isay
    -0.16
    imum
    -0.15
    antha
    -0.15
    ease
    -0.15
    arih
    -0.15
    imity
    -0.15
    paque
    -0.15
    POSITIVE LOGITS
    ales
    0.19
    ematic
    0.19
    inned
    0.18
    omas
    0.18
    orough
    0.17
     rough
    0.17
    rought
    0.17
    ATER
    0.17
    wart
    0.16
    ink
    0.16
    Act Density 0.031%

    No Known Activations