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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that express intentions or future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.99
    InputBorder
    -0.93
    WebVitals
    -0.86
     ModelExpression
    -0.84
    mybatisplus
    -0.84
     stinks
    -0.82
     المعيارى
    -0.82
     fucking
    -0.80
     messing
    -0.79
     shitty
    -0.78
    POSITIVE LOGITS
     further
    0.63
     significantly
    0.59
     provide
    0.57
     substantially
    0.57
     also
    0.53
     closely
    0.47
     provides
    0.46
     särskilt
    0.46
     thereby
    0.45
     frequently
    0.45
    Act Density 0.765%

    No Known Activations