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

    Neuronpedia

    INDEX
    Explanations

    contractions indicating future actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’s
    -0.30
    /or
    -0.21
    ’n
    -0.21
    ’re
    -0.21
    ’S
    -0.20
    ‘s
    -0.20
    ´s
    -0.19
     latter
    -0.19
    ’t
    -0.19
    ’m
    -0.18
    POSITIVE LOGITS
    /'
    0.27
    '
    0.25
     '
    0.23
    'll
    0.23
    ÂĿ
    0.23
    ')
    0.20
    amp
    0.20
    've
    0.19
    -'
    0.19
    gether
    0.19
    Act Density 0.097%

    No Known Activations