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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the number of stories in buildings

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of stories in buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibaba
    -0.86
    aez
    -0.80
    icion
    -0.68
    ktop
    -0.68
    ugal
    -0.67
    istered
    -0.67
    ocol
    -0.67
    opard
    -0.67
    gotten
    -0.66
    argon
    -0.65
    POSITIVE LOGITS
    tall
    0.85
    boards
    0.81
     tall
    0.79
     arc
    0.79
     tallest
    0.78
     buildings
    0.78
     ceilings
    0.73
    board
    0.72
    Fair
    0.69
     Corinth
    0.69
    Act Density 0.020%

    No Known Activations