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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or unexpected reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ?}",
    -0.73
     tartalomajánló
    -0.64
    -};
    -0.62
    ();)
    -0.62
    ⋱
    -0.60
    openzeppelin
    -0.59
    Opus
    -0.59
    :])
    -0.58
    ScopeManager
    -0.57
    #+#
    -0.57
    POSITIVE LOGITS
     shocked
    1.91
     amazed
    1.67
     surprised
    1.66
     astonished
    1.65
     stunned
    1.62
     annoyed
    1.59
     horrified
    1.59
     delighted
    1.58
     disappointed
    1.57
     thrilled
    1.56
    Act Density 0.128%

    No Known Activations