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

    Neuronpedia

    INDEX
    Explanations

    social media handles and points systems

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the phrase "haven't" in the context of unfulfilled actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prone
    -0.70
     Lynd
    -0.69
     Swordsman
    -0.66
     Yad
    -0.65
    åħī
    -0.63
     Hir
    -0.63
     Amit
    -0.63
    çīĪ
    -0.62
     complicit
    -0.61
     unworthy
    -0.59
    POSITIVE LOGITS
    been
    1.17
    since
    0.85
    undreds
    0.77
     been
    0.77
    ample
    0.74
    yet
    0.69
    many
    0.68
    Constructed
    0.67
    wait
    0.66
    gui
    0.66
    Act Density 0.039%

    No Known Activations