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

    Neuronpedia

    INDEX
    Explanations

    phrases related to directions or courses of action

    oai_token-act-pair · gpt-3.5-turbo

    references to various metaphorical paths and directions in relation to decision-making or progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arer
    -0.75
    rab
    -0.66
    onga
    -0.65
    aband
    -0.65
    ban
    -0.63
    tab
    -0.62
     stub
    -0.61
    hib
    -0.59
    uled
    -0.57
     bans
    -0.57
    POSITIVE LOGITS
     financially
    0.80
    leon
    0.78
     heights
    0.73
     creatively
    0.73
     spiritually
    0.73
    elight
    0.69
     athlet
    0.68
    erness
    0.67
     emotionally
    0.67
     mindset
    0.66
    Act Density 0.178%

    No Known Activations