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

    Neuronpedia

    INDEX
    Explanations

    phrases related to features and specifications

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "it" used to refer to various subjects or objects throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ©ãĥ³
    -0.75
    911
    -0.72
     Friend
    -0.68
     Guant
    -0.68
     Breast
    -0.68
    inqu
    -0.66
    dding
    -0.64
    noon
    -0.63
     Transcript
    -0.62
    Priv
    -0.62
    POSITIVE LOGITS
    alian
    1.16
    chy
    1.05
    unes
    1.04
    self
    0.99
    asca
    0.98
    anium
    0.86
     ain
    0.85
     seems
    0.85
    atic
    0.83
     conduc
    0.82
    Act Density 0.448%

    No Known Activations