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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     continents
    -1.80
     forty
    -1.69
     pros
    -1.67
     earth
    -1.64
     thirty
    -1.62
    enth
    -1.56
     boats
    -1.56
    except
    -1.55
     dwell
    -1.55
     fifty
    -1.52
    POSITIVE LOGITS
    Ĩ
    3.36
    ij
    3.33
    ¿½
    3.25
    ¡
    3.24
    ¨
    3.21
    ·¸
    3.17
    ½
    3.16
    µ
    3.15
    ©
    3.12
    ¿
    3.10
    Act Density 1.000%

    No Known Activations