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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sign" as a strong match

    oai_token-act-pair · gpt-3.5-turbo

    the word "sign" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĨij
    -0.77
    Series
    -0.72
    OOD
    -0.71
    URR
    -0.67
    enne
    -0.66
    ooked
    -0.66
    =~=~
    -0.66
    ETHOD
    -0.65
     ILCS
    -0.65
    BILITIES
    -0.65
    POSITIVE LOGITS
     sign
    1.32
    atories
    1.23
     Sign
    1.10
     signs
    1.07
    sign
    1.07
     Signs
    1.03
    Sign
    0.93
    posts
    0.90
    atory
    0.88
    ifiers
    0.87
    Act Density 0.015%

    No Known Activations