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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to observation and commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isle
    -0.19
    >NN
    -0.15
    ened
    -0.15
    spiel
    -0.15
    -legged
    -0.15
    .AutoScaleMode
    -0.14
    ouz
    -0.14
    ò
    -0.14
    worth
    -0.14
    ahun
    -0.14
    POSITIVE LOGITS
    å¯Ł
    0.22
    vation
    0.20
    /me
    0.19
    ably
    0.19
    à¸ģารà¸ĵ
    0.19
    (obs
    0.18
    ances
    0.18
     observation
    0.18
    /list
    0.17
    297
    0.17
    Act Density 0.027%

    No Known Activations