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

    Neuronpedia

    INDEX
    Explanations

    physical movement actions or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    contexts relating to personal experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ranch
    -0.67
     themselves
    -0.64
    cil
    -0.60
    uf
    -0.58
    enz
    -0.58
    ighed
    -0.57
     omin
    -0.57
    DragonMagazine
    -0.57
    entry
    -0.56
     ousted
    -0.56
    POSITIVE LOGITS
     myself
    1.29
     my
    1.16
     I
    1.06
     My
    1.00
    My
    0.84
    I
    0.79
     haha
    0.70
    my
    0.69
    laughs
    0.69
     Dying
    0.67
    Act Density 0.749%

    No Known Activations