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

    Neuronpedia

    INDEX
    Explanations

    mentions of the phrase "straw man."

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "straw" and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apse
    -0.82
    olon
    -0.78
    olitan
    -0.72
     notor
    -0.69
     Reloaded
    -0.69
    ynt
    -0.69
    ogue
    -0.67
    apses
    -0.65
    ativity
    -0.65
    aky
    -0.64
    POSITIVE LOGITS
     straw
    0.95
    weight
    0.93
    poll
    0.91
    mere
    0.89
    berries
    0.87
    backs
    0.87
    weights
    0.87
    sided
    0.82
    bare
    0.81
    pipe
    0.80
    Act Density 0.051%

    No Known Activations