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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and decisions

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or statements indicating emphasis or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arthed
    -0.75
     ®
    -0.74
    âĦ¢:
    -0.69
    WAR
    -0.67
    è¦ļéĨĴ
    -0.66
    ivist
    -0.62
    Pg
    -0.61
    *:
    -0.60
    ailable
    -0.58
    idden
    -0.58
    POSITIVE LOGITS
     ..."
    0.92
     mathemat
    0.84
     [
    0.82
     gotta
    0.78
    .""
    0.76
    )."
    0.76
     competitiveness
    0.74
    cknow
    0.73
    entimes
    0.73
     ain
    0.71
    Act Density 0.368%

    No Known Activations