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

    Neuronpedia

    INDEX
    Explanations

    phrases related to warning signals or alerts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "red."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UGH
    -0.78
    ernel
    -0.76
    awaru
    -0.74
    Ö¼
    -0.74
    XT
    -0.71
     Lank
    -0.71
    ILA
    -0.69
    Reloaded
    -0.65
     4090
    -0.65
    agall
    -0.65
    POSITIVE LOGITS
    efined
    1.21
    neck
    1.19
    oubt
    1.17
    iscovered
    1.16
    irection
    1.14
    oub
    1.10
    ucing
    1.08
    iscover
    1.07
    rawn
    1.07
    iscovery
    1.06
    Act Density 0.027%

    No Known Activations