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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe the composition or structure of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ironically
    -0.47
     שוליים
    -0.46
     condicion
    -0.41
    脚注の使い方
    -0.40
     späteren
    -0.40
    AppState
    -0.40
     perlindungan
    -0.39
    certainly
    -0.39
     obliquely
    -0.39
    attenzione
    -0.39
    POSITIVE LOGITS
     consisting
    1.49
     consists
    1.48
     consisted
    1.48
     comprised
    1.36
     consist
    1.36
     composed
    1.28
     comprising
    1.22
     består
    1.21
     comprises
    1.20
     terdiri
    1.15
    Act Density 0.476%

    No Known Activations