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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions or feelings in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     centrif
    -0.73
     interchange
    -0.66
     shocks
    -0.66
     Dragonbound
    -0.63
     loophole
    -0.61
     penetration
    -0.60
     diffusion
    -0.60
     displacement
    -0.60
     exposure
    -0.59
     Colossus
    -0.58
    POSITIVE LOGITS
    Ĩ
    1.40
    ¹
    1.38
    Į
    1.36
    İ
    1.36
    ĺ
    1.31
    ¿
    1.31
    ī
    1.29
    ĥ
    1.29
    »
    1.28
    «
    1.28
    Act Density 0.009%

    No Known Activations