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

    Neuronpedia

    INDEX
    Explanations

    specific acronyms or codes

    oai_token-act-pair · gpt-3.5-turbo

    recurring phrases or abbreviations for "LE" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulas
    -0.81
    papers
    -0.80
    ilities
    -0.78
    oulos
    -0.76
    ãĤ¢ãĥ«
    -0.75
    ulators
    -0.72
    ̶
    -0.72
    arian
    -0.70
    ulating
    -0.69
    ipation
    -0.68
    POSITIVE LOGITS
    lean
    0.97
    VEL
    0.87
    ASE
    0.86
    ttes
    0.83
    prints
    0.82
    IGH
    0.82
    asure
    0.79
    teen
    0.77
    ASED
    0.76
    VIEW
    0.75
    Act Density 0.041%

    No Known Activations