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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the significance or impact of a particular event or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant experiences or defining moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disposed
    -0.63
    hya
    -0.63
    ensen
    -0.59
    ');
    -0.56
     aside
    -0.56
    lean
    -0.54
     passer
    -0.54
    ville
    -0.54
    culosis
    -0.53
    GL
    -0.52
    POSITIVE LOGITS
    icial
    0.69
     Ragnarok
    0.62
     nerv
    0.61
    ruary
    0.60
    terness
    0.59
     Decay
    0.58
    arching
    0.58
     simplest
    0.57
     strang
    0.57
    ron
    0.57
    Act Density 0.087%

    No Known Activations