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

    Neuronpedia

    INDEX
    Explanations

    instances of emotive expressions or sentiments within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by punctuation or a number

    np_acts-logits-general · gemini-2.0-flash

    Carpenter, burden, rions, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noemen
    -0.51
    ureusement
    -0.51
    Außerdem
    -0.48
     Außerdem
    -0.47
     تانيه
    -0.46
    zkod
    -0.46
    eluarkan
    -0.45
     mierda
    -0.45
     correctement
    -0.45
     asesoramiento
    -0.44
    POSITIVE LOGITS
    脚注の使い方
    0.81
    annica
    0.74
    جغرافيا
    0.64
     teu
    0.63
     FetchType
    0.63
    ymce
    0.63
    ArgsConstructor
    0.62
     rap
    0.61
    VIAF
    0.61
    nestjs
    0.60
    Act Density 0.076%

    No Known Activations