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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of need or desire for further action or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a lack of additional information or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.81
    ertodd
    -0.80
    ocl
    -0.72
    ldom
    -0.72
    inho
    -0.72
    orno
    -0.68
     gripped
    -0.66
    emet
    -0.66
    ĪĴ
    -0.65
    pi
    -0.65
    POSITIVE LOGITS
     ado
    1.16
     advances
    0.87
     delay
    0.87
     advance
    0.87
     interruption
    0.87
     advancement
    0.85
    ance
    0.85
     developments
    0.81
     clarification
    0.78
     consideration
    0.78
    Act Density 0.039%

    No Known Activations