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

    Neuronpedia

    INDEX
    Explanations

    phrases that relate to associations and dependencies between variables or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     t
    -0.45
     outra
    -0.45
     et
    -0.44
     h
    -0.42
     altra
    -0.42
    alih
    -0.42
     otra
    -0.41
    sa
    -0.40
    他に
    -0.40
    q
    -0.40
    POSITIVE LOGITS
     Efq
    0.97
    ſelf
    0.89
     iſt
    0.88
     Majefty
    0.87
     myſelf
    0.84
     itſelf
    0.83
     ་་
    0.83
     crdi
    0.83
     houſe
    0.82
     ſind
    0.81
    Act Density 0.855%

    No Known Activations