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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating expectations or hopes

    oai_token-act-pair · gpt-3.5-turbo

    expressions of expectation and planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     understands
    -0.68
    ravings
    -0.67
     compares
    -0.65
     varies
    -0.63
     consumes
    -0.61
    Witness
    -0.60
    ounces
    -0.60
     interacts
    -0.59
     matters
    -0.58
    orio
    -0.58
    POSITIVE LOGITS
     hoped
    0.86
     doom
    0.75
     earlier
    0.70
    ndra
    0.68
     planned
    0.67
     Manor
    0.67
     unsuccessfully
    0.63
     beforehand
    0.63
    bone
    0.62
     invincible
    0.61
    Act Density 0.435%

    No Known Activations