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

    Neuronpedia

    INDEX
    Explanations

    negative constructions and expressions of disappointment or inadequacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nl
    -0.15
    enheim
    -0.15
     possibile
    -0.15
    kenin
    -0.15
    daq
    -0.15
    GI
    -0.15
    meer
    -0.15
    okers
    -0.15
    atar
    -0.14
    issement
    -0.14
    POSITIVE LOGITS
     bad
    0.25
     outright
    0.24
     Bad
    0.23
     BAD
    0.21
    _bad
    0.20
     necessarily
    0.20
    Bad
    0.19
    icÃŃ
    0.17
    .scalablytyped
    0.17
    bad
    0.17
    Act Density 0.185%

    No Known Activations