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

    Neuronpedia

    INDEX
    Explanations

    the phrase structure that indicates future actions and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ist
    -0.82
    *************
    -0.79
    Abitanti
    -0.74
    ****************
    -0.72
     has
    -0.71
     is
    -0.70
    **************
    -0.67
     Barlow
    -0.67
     awak
    -0.65
    has
    -0.64
    POSITIVE LOGITS
     pleaſure
    0.96
     purpoſe
    0.94
     youll
    0.89
     myſelf
    0.88
     houſe
    0.85
     ſtate
    0.85
     themſelves
    0.85
    Howdy
    0.84
     ſche
    0.83
     juſt
    0.83
    Act Density 0.042%

    No Known Activations