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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing emotional states or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.15
    enderror
    -0.91
    RegressionTest
    -0.89
    ⓧ
    -0.86
    LookAnd
    -0.85
     متعلقه
    -0.85
    YourGuide
    -0.84
    sidemargin
    -0.81
    IUrlHelper
    -0.80
    DockStyle
    -0.79
    POSITIVE LOGITS
     enough
    0.95
     to
    0.87
     for
    0.80
     in
    0.71
     and
    0.67
     from
    0.63
     going
    0.58
     about
    0.57
    夠
    0.55
    ,
    0.54
    Act Density 0.704%

    No Known Activations