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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial situations and consequences

    oai_token-act-pair · gpt-3.5-turbo

    negative or critical statements about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REDACTED
    -0.67
    osure
    -0.59
     nutshell
    -0.59
    WER
    -0.52
    atus
    -0.51
    soDeliveryDate
    -0.50
    ¬¼
    -0.50
     retrospect
    -0.50
    ural
    -0.50
    endum
    -0.50
    POSITIVE LOGITS
     whereas
    0.78
    often
    0.74
     Conversely
    0.69
    selves
    0.64
     Especially
    0.63
     regardless
    0.63
     irrespective
    0.63
     They
    0.63
     moreover
    0.62
     beware
    0.62
    Act Density 0.804%

    No Known Activations