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

    Neuronpedia

    INDEX
    Explanations

    words related to increasing or escalating situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a rising trend or escalation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieu
    -0.84
    quote
    -0.77
    tein
    -0.75
    gio
    -0.72
    ican
    -0.71
    aign
    -0.71
    tan
    -0.71
    vision
    -0.70
     Polo
    -0.70
    rug
    -0.67
    POSITIVE LOGITS
     frustrated
    0.98
     increasingly
    0.87
     dissatisfied
    0.86
     millenn
    0.86
     cumbers
    0.84
     inactive
    0.82
     impatient
    0.82
     phased
    0.82
     enthusi
    0.82
     extinct
    0.81
    Act Density 0.012%

    No Known Activations