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

    Neuronpedia

    INDEX
    Explanations

    phrases related to perspectives or intentions

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

    phrases indicating purpose or intention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Breath
    -0.38
     Infectious
    -0.37
    infe
    -0.36
     phụ
    -0.35
     Reb
    -0.35
    chall
    -0.35
     infectious
    -0.35
     Usar
    -0.35
     inf
    -0.34
     Donat
    -0.34
    POSITIVE LOGITS
     aiming
    0.75
     aimed
    0.73
    twimg
    0.72
     aim
    0.70
     <<<<<<<<<<<<<<
    0.69
     Hinblick
    0.68
    endphp
    0.67
     visant
    0.65
    uxxxx
    0.63
    存于互联网档案馆
    0.62
    Act Density 0.049%

    No Known Activations