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

    Neuronpedia

    INDEX
    Explanations

    terms indicating subjective evaluations or feelings related to quality and performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ?>">
    -0.54
    expandindo
    -0.52
     kommunen
    -0.51
     Cæsar
    -0.51
     countless
    -0.50
     absolutamente
    -0.50
    copyOf
    -0.49
    !("
    -0.49
     }}>
    -0.49
    勿論
    -0.47
    POSITIVE LOGITS
     BorderSide
    0.81
     المعيارى
    0.80
    somewhat
    0.78
    fortunate
    0.75
     noDo
    0.73
    ISupport
    0.72
     somewhat
    0.69
     nieco
    0.69
     agak
    0.69
    complexContent
    0.68
    Act Density 0.285%

    No Known Activations