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

    Neuronpedia

    INDEX
    Explanations

    concepts related to crime and unethical behavior

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AlterField
    -0.84
    Datuak
    -0.82
    +#+#
    -0.82
    AutoScaleMode
    -0.81
    makeConstraints
    -0.81
     autorytatywna
    -0.79
     виправивши
    -0.77
    expandindo
    -0.76
    principalColumn
    -0.76
    omla
    -0.75
    POSITIVE LOGITS
     finest
    0.75
     worst
    0.49
    tto
    0.48
     latest
    0.47
     imaginable
    0.46
     strictest
    0.46
     cuidadosamente
    0.46
     przer
    0.46
    LEncoder
    0.45
     newest
    0.44
    Act Density 0.032%

    No Known Activations