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

    Neuronpedia

    INDEX
    Explanations

    expressions of hope and encouragement in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    must
    -0.71
     prácticamente
    -0.69
     praticamente
    -0.69
     likely
    -0.68
     undoubtedly
    -0.68
     almost
    -0.67
    almost
    -0.67
     probably
    -0.67
     presumably
    -0.67
    probably
    -0.67
    POSITIVE LOGITS
     someday
    0.86
    ValueStyle
    0.73
     gelingt
    0.69
    RTLD
    0.69
     بتوان
    0.67
    能让
    0.67
     wenigstens
    0.65
     algún
    0.65
    能在
    0.64
     beginnetje
    0.64
    Act Density 0.198%

    No Known Activations