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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or ambiguity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     дописавши
    -0.59
    httphttps
    -0.53
    legende
    -0.47
     gynhyrchwyd
    -0.47
    جغرافيا
    -0.47
     Hewitt
    -0.45
    ässe
    -0.45
    owned
    -0.45
    جوايز
    -0.45
     referrerpolicy
    -0.44
    POSITIVE LOGITS
     apparente
    0.96
     seeming
    0.77
     seemingly
    0.75
     aparente
    0.73
    看似
    0.68
    Facades
    0.68
    WithIdentifier
    0.67
    toid
    0.65
     Seem
    0.63
     aparentemente
    0.62
    Act Density 0.316%

    No Known Activations