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

    Neuronpedia

    INDEX
    Explanations

    sentences that express a positive sentiment or favorable evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adden
    -0.18
     lookahead
    -0.17
     Hear
    -0.17
     glance
    -0.16
     overhe
    -0.16
     glimps
    -0.16
    azzi
    -0.16
    åIJ¬åĪ°
    -0.16
     hearing
    -0.16
    uito
    -0.15
    POSITIVE LOGITS
     se
    0.30
    -se
    0.27
    ese
    0.25
     SE
    0.22
     seem
    0.22
    sec
    0.22
     sec
    0.21
     SEC
    0.20
     seam
    0.19
     scene
    0.19
    Act Density 0.091%

    No Known Activations