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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or potential actions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating direction or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tracker
    -0.65
    iola
    -0.65
    wcs
    -0.65
    quad
    -0.65
    breaks
    -0.64
    walk
    -0.64
    heartedly
    -0.64
    fortunately
    -0.62
    tek
    -0.62
    echo
    -0.62
    POSITIVE LOGITS
     nonex
    0.77
     oneself
    0.74
     conformity
    0.70
    effic
    0.70
     mortality
    0.67
     quo
    0.67
     Responsibility
    0.66
    emonic
    0.63
    rimination
    0.62
    itability
    0.61
    Act Density 0.343%

    No Known Activations