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

    Neuronpedia

    INDEX
    Explanations

    phrases related to futuristic advancements and technological innovations

    oai_token-act-pair · gpt-3.5-turbo

    symbols and non-standard characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shack
    -0.79
     touches
    -0.72
     closest
    -0.72
     shrouded
    -0.71
     lodging
    -0.71
     sofa
    -0.71
     boarding
    -0.70
     couch
    -0.69
     cottage
    -0.69
     cyan
    -0.69
    POSITIVE LOGITS
    º
    1.17
    £
    1.08
    ¬
    1.06
    ¹
    1.01
    ¡
    0.98
    ONSORED
    0.95
    Ĵ
    0.93
    Ĥ
    0.92
    ķ
    0.91
    ®
    0.91
    Act Density 0.129%

    No Known Activations