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

    Neuronpedia

    INDEX
    Explanations

    phrases related to contrasting choices or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating exclusivity or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oro
    -0.69
    amon
    -0.67
    },"
    -0.63
    rament
    -0.62
    eg
    -0.61
    âĿ
    -0.61
    ender
    -0.61
     Sunshine
    -0.60
    atur
    -0.60
    izens
    -0.59
    POSITIVE LOGITS
     preferring
    0.91
     implying
    0.84
     suggesting
    0.84
     culminating
    0.79
     skipping
    0.77
    christ
    0.76
     guaranteeing
    0.76
     excluding
    0.76
     allowing
    0.74
     adolesc
    0.72
    Act Density 0.361%

    No Known Activations