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

    Neuronpedia

    INDEX
    Explanations

    the word "some" followed by either a noun or a verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the presence of certain quantities or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    buster
    -0.76
     theirs
    -0.70
    hands
    -0.69
    ©¶æ
    -0.64
    ãĥł
    -0.63
    Phones
    -0.62
    gypt
    -0.61
    enance
    -0.61
    Ts
    -0.61
    ires
    -0.60
    POSITIVE LOGITS
     overlap
    1.14
     exceptions
    0.86
     similarities
    0.83
     disagreement
    0.83
     chance
    0.82
     consolation
    0.82
     caveat
    0.81
     differences
    0.79
     tendency
    0.79
     temptation
    0.78
    Act Density 0.106%

    No Known Activations