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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases about monetary compensation and value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
     resp
    -0.60
     presumed
    -0.60
     coinc
    -0.56
     nu
    -0.56
     suspected
    -0.54
    vernment
    -0.54
     bung
    -0.53
    racuse
    -0.52
    è£ħ
    -0.52
    POSITIVE LOGITS
    ł
    0.85
    ¹
    0.74
    ¥
    0.71
    £
    0.68
    ¡
    0.68
    IJ
    0.68
    ĺ
    0.68
    Laughs
    0.66
    laughs
    0.66
    Certainly
    0.65
    Act Density 0.367%

    No Known Activations