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

    Neuronpedia

    INDEX
    Explanations

    common prepositions and conjunctions used in the text

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

    prepositions for location or direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.55
    ſelf
    -0.54
     himſelf
    -0.54
     enfans
    -0.54
    leſs
    -0.52
     myſelf
    -0.52
    脚注の使い方
    -0.51
    cplusplus
    -0.49
     Jefus
    -0.48
     neceſſ
    -0.47
    POSITIVE LOGITS
     in
    0.89
     In
    0.75
     at
    0.71
     on
    0.69
     inside
    0.68
     در
    0.65
    ใน
    0.63
     @"/
    0.63
     Di
    0.63
     At
    0.63
    Act Density 0.001%

    No Known Activations