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

    Neuronpedia

    INDEX
    Explanations

    emotional responses and expressions of concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADDE
    -0.18
    ationToken
    -0.17
     Hindered
    -0.16
    dda
    -0.16
    νι
    -0.16
    DebugEnabled
    -0.15
    ATAB
    -0.15
     Erotische
    -0.14
    ipse
    -0.14
     Neck
    -0.14
    POSITIVE LOGITS
     liv
    0.34
     app
    0.31
     mort
    0.30
     pert
    0.30
     crest
    0.27
     inc
    0.26
     upset
    0.25
     chees
    0.25
    liv
    0.23
    crest
    0.23
    Act Density 0.270%

    No Known Activations