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

    Neuronpedia

    INDEX
    Explanations

    phrases related to communication and conversation

    oai_token-act-pair · gpt-3.5-turbo

    conversational phrases and expressions of sentiment or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     comprehens
    -0.72
    ãĢij
    -0.71
    åĨ
    -0.69
    Information
    -0.69
    ItemImage
    -0.69
     ESA
    -0.66
    ISC
    -0.66
    é¾įå¥ij士
    -0.65
     ASUS
    -0.65
    Individual
    -0.65
    POSITIVE LOGITS
     ain
    1.50
     fuckin
    1.42
     ya
    1.37
     gon
    1.37
     nig
    1.35
     wanna
    1.31
    tin
    1.30
    nin
    1.27
     somet
    1.25
    hin
    1.23
    Act Density 0.378%

    No Known Activations