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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rules, responsibilities, adherence to standards, and consequences of actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ifter
    -0.71
     Croat
    -0.71
     beans
    -0.69
     Crusader
    -0.67
    boa
    -0.67
    andel
    -0.66
    AIN
    -0.66
     Straw
    -0.66
    fly
    -0.63
     Rasmussen
    -0.63
    POSITIVE LOGITS
     thereto
    1.51
    xual
    1.00
    entious
    0.98
     unto
    0.94
    pires
    0.93
    itiz
    0.91
    gypt
    0.89
    lectic
    0.82
    ÃĽ
    0.82
    imus
    0.82
    Act Density 2.534%

    No Known Activations