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

    Neuronpedia

    INDEX
    Explanations

    sentences describing a state of being or an action taken

    oai_token-act-pair · gpt-3.5-turbo

    themes related to life-or-death situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Firstly
    -0.77
     Whilst
    -0.70
     Firstly
    -0.64
     ðŁĺ
    -0.57
     whilst
    -0.57
     haha
    -0.56
    [/
    -0.56
     Yep
    -0.55
     honour
    -0.55
    .#
    -0.53
    POSITIVE LOGITS
    armor
    0.53
    ichever
    0.53
     restitution
    0.50
    hovah
    0.50
    avez
    0.50
    urance
    0.50
    rely
    0.49
    ologic
    0.49
     nonex
    0.48
    cellaneous
    0.47
    Act Density 1.931%

    No Known Activations