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

    Neuronpedia

    INDEX
    Explanations

    general statements about various subjects or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artige
    -0.43
    搞笑
    -0.41
     rare
    -0.41
    Predicate
    -0.40
     Pohl
    -0.40
    nostic
    -0.39
     Lithuanian
    -0.38
    Field
    -0.38
     $('<
    -0.38
     "
    -0.37
    POSITIVE LOGITS
     Everything
    1.27
    everything
    1.26
     everything
    1.23
    Everything
    1.23
     everyone
    1.18
    everyone
    1.14
     Everyone
    1.13
     EVERYTHING
    1.13
    Everyone
    1.10
     EVERYONE
    1.10
    Act Density 0.104%

    No Known Activations