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

    Neuronpedia

    INDEX
    Explanations

    words related to negative outcomes or worsening situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a decline or worsening situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ij士
    -0.73
    ools
    -0.71
    cot
    -0.65
    cock
    -0.65
    romy
    -0.61
    poke
    -0.61
    OPLE
    -0.59
    esp
    -0.59
    itle
    -0.58
    ouch
    -0.58
    POSITIVE LOGITS
     exponentially
    0.84
     progressively
    0.81
     veter
    0.73
     steadily
    0.71
     each
    0.70
     gradually
    0.69
     than
    0.69
     yearly
    0.68
     every
    0.65
    Winged
    0.65
    Act Density 0.127%

    No Known Activations