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

    Neuronpedia

    INDEX
    Explanations

    sentences starting with specific symbols or capital letters

    oai_token-act-pair · gpt-3.5-turbo

    phrases or expressions indicating clarity or certainty in a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.68
     capsule
    -0.66
     srfAttach
    -0.60
    etheless
    -0.60
     fixture
    -0.59
     variance
    -0.59
     Glou
    -0.59
     reception
    -0.58
     tremend
    -0.58
    erning
    -0.57
    POSITIVE LOGITS
    ymes
    0.87
    acca
    0.82
    istan
    0.82
    kamp
    0.76
    ¹
    0.73
    ebook
    0.72
    bec
    0.71
    ¬
    0.70
    º
    0.68
    ghan
    0.68
    Act Density 0.223%

    No Known Activations