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

    Neuronpedia

    INDEX
    Explanations

    sentences that convey a variety of emotional tones or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     concess
    -0.83
     clin
    -0.75
     implication
    -0.72
     gravy
    -0.71
    iman
    -0.70
     exped
    -0.69
     voluntarily
    -0.68
    idth
    -0.67
    å§
    -0.66
    ratulations
    -0.66
    POSITIVE LOGITS
     Whereas
    1.39
     Instead
    1.36
     Nonetheless
    1.33
     Nevertheless
    1.27
     Firstly
    1.22
     Aside
    1.19
     Luckily
    1.18
     Though
    1.18
     Unlike
    1.17
     Despite
    1.16
    Act Density 0.210%

    No Known Activations