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

    Neuronpedia

    INDEX
    Explanations

    sentences or statements indicating questions or thoughts about the natural world

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ***!
    -0.51
     Comunicación
    -0.50
    sipasi
    -0.48
    Thunk
    -0.47
    ండి
    -0.46
    brainly
    -0.45
     telefónica
    -0.44
    tka
    -0.43
    hashi
    -0.43
    cetti
    -0.43
    POSITIVE LOGITS
    adaptiveStyles
    0.90
     nature
    0.84
    Natur
    0.79
     natural
    0.78
     natur
    0.77
     natu
    0.76
    protoimpl
    0.76
     natura
    0.75
    natur
    0.75
    Nature
    0.74
    Act Density 0.235%

    No Known Activations