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

    Neuronpedia

    INDEX
    Explanations

    patterns of criticism and skepticism directed towards social and economic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Künst
    -0.52
     permitan
    -0.48
    िक्ष
    -0.48
    żli
    -0.47
     Soccerway
    -0.46
    وفاته
    -0.45
    تقاوى
    -0.44
    krank
    -0.44
     AssemblyTitle
    -0.44
    NgModule
    -0.44
    POSITIVE LOGITS
     claiming
    0.77
     claims
    0.77
     rhetoric
    0.72
     argument
    0.70
     dizendo
    0.69
     betweenstory
    0.68
     arguing
    0.67
     hype
    0.67
    Saying
    0.67
    claims
    0.66
    Act Density 0.440%

    No Known Activations