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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "much" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.77
    etts
    -0.76
    emen
    -0.75
    İĭ
    -0.73
    akings
    -0.69
    ģĸ
    -0.69
     Butterfly
    -0.69
    worn
    -0.68
    jac
    -0.68
    ems
    -0.67
    POSITIVE LOGITS
    antz
    0.73
     effort
    0.69
     tract
    0.66
     tracts
    0.64
     than
    0.63
     practicable
    0.63
     AS
    0.62
     diverse
    0.61
     popcorn
    0.60
     anticipated
    0.60
    Act Density 0.036%

    No Known Activations