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

    Neuronpedia

    INDEX
    Explanations

    various expressions of personal struggle and resilience

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

    we pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelves
    -0.54
     pleaſure
    -0.52
     viſ
    -0.52
     ſta
    -0.49
     externa
    -0.48
     Houſe
    -0.47
    ſelf
    -0.47
     houſe
    -0.46
     external
    -0.45
     inſ
    -0.45
    POSITIVE LOGITS
     للمعارف
    0.54
     <<<<<<<<<<<<<<
    0.44
     itulah
    0.42
     '\\;'
    0.42
     coupable
    0.41
    transQ
    0.40
    #+#
    0.40
    saraba
    0.40
    invokeLater
    0.40
     impresión
    0.39
    Act Density 0.013%

    No Known Activations