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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate change or progression

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases indicating decline or deterioration in social or economic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sol
    -0.65
    stra
    -0.62
    wd
    -0.62
    arta
    -0.61
    POL
    -0.59
    Reference
    -0.58
    hold
    -0.56
    osal
    -0.56
    square
    -0.56
    uristic
    -0.56
    POSITIVE LOGITS
     exponentially
    0.86
     explos
    0.81
    icter
    0.78
    IER
    0.78
     downhill
    0.76
     territ
    0.75
     spontaneously
    0.73
     abruptly
    0.70
    amorph
    0.70
     organ
    0.70
    Act Density 0.245%

    No Known Activations