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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to expressing strong emotions or criticisms

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions of condemnation or rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zo
    -0.68
     TEXT
    -0.64
    .}
    -0.63
    til
    -0.63
    zon
    -0.59
    lyss
    -0.59
     WITHOUT
    -0.59
     entertained
    -0.59
     suppose
    -0.58
    poral
    -0.58
    POSITIVE LOGITS
     discredit
    0.84
    igated
    0.79
     aside
    0.78
     blame
    0.78
     Patel
    0.76
     scorn
    0.76
     havoc
    0.73
     out
    0.73
    ocrats
    0.70
    igate
    0.69
    Act Density 0.123%

    No Known Activations