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

    Neuronpedia

    INDEX
    Explanations

    phrases related to playful teasing or provocation

    oai_token-act-pair · gpt-3.5-turbo

    references to playful or critical commentary, often using the word "poke."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingham
    -0.91
    recy
    -0.74
    inction
    -0.68
    Percent
    -0.67
    icter
    -0.66
    Decl
    -0.65
    gray
    -0.65
    uther
    -0.65
    ifted
    -0.63
    eded
    -0.63
    POSITIVE LOGITS
     poking
    0.99
     poke
    0.92
     holes
    0.80
     peek
    0.80
    ature
    0.79
    cheon
    0.75
    asso
    0.72
     recess
    0.71
    geon
    0.71
     poked
    0.70
    Act Density 0.042%

    No Known Activations