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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating a preference or choice

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating preferences or actions related to doing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LINE
    -0.69
    CCC
    -0.66
    RANT
    -0.64
     Greenpeace
    -0.61
     pandemonium
    -0.61
    NP
    -0.59
     flagged
    -0.57
     wildfire
    -0.57
     organizer
    -0.56
     breached
    -0.56
    POSITIVE LOGITS
    ahime
    0.84
    wcsstore
    0.81
    ardless
    0.77
     ç¥ŀ
    0.72
    asty
    0.72
     seiz
    0.71
    ecause
    0.70
    than
    0.69
    ilitarian
    0.68
     defer
    0.66
    Act Density 0.209%

    No Known Activations