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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exclusivity or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \{\\
    -0.67
     <<<<<<<<<<<<<<
    -0.65
    };*/
    -0.61
    Einzelnachweise
    -0.61
    /*++
    -0.60
    ocarditis
    -0.60
     rowspan
    -0.60
    exus
    -0.57
    Vanjske
    -0.56
    nesc
    -0.55
    POSITIVE LOGITS
    only
    0.87
     only
    0.85
     лишь
    0.84
    Only
    0.82
     Only
    0.82
    только
    0.81
     ONLY
    0.77
    ONLY
    0.76
     незавершена
    0.74
     Только
    0.74
    Act Density 0.257%

    No Known Activations