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

    Neuronpedia

    INDEX
    Explanations

    phrases related to passive-aggressiveness

    oai_token-act-pair · gpt-3.5-turbo

    references to passive behaviors or attitudes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AMI
    -0.78
    ograp
    -0.77
    esan
    -0.72
    ĸļ
    -0.71
    Issue
    -0.68
    ographers
    -0.68
     Lob
    -0.67
    ographics
    -0.64
     Banner
    -0.64
     Yiannopoulos
    -0.63
    POSITIVE LOGITS
     Passive
    0.91
     minded
    0.89
    aggressive
    0.88
    comm
    0.81
     passive
    0.79
    ives
    0.77
    wd
    0.75
     reactive
    0.74
     aggressive
    0.74
    getic
    0.72
    Act Density 0.019%

    No Known Activations