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

    Neuronpedia

    INDEX
    Explanations

    phrases related to potential future consequences and emotional burdens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rena
    -0.17
    AMP
    -0.16
    edy
    -0.16
    ennes
    -0.16
    lsi
    -0.15
    dit
    -0.15
    _INCLUDED
    -0.15
    /***/
    -0.14
    preced
    -0.14
    115
    -0.13
    POSITIVE LOGITS
     later
    0.71
     down
    0.67
     Later
    0.58
    later
    0.57
    Later
    0.54
     Down
    0.50
     später
    0.49
     future
    0.49
    Down
    0.47
    down
    0.45
    Act Density 0.209%

    No Known Activations