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

    Neuronpedia

    INDEX
    Explanations

    first-person personal statements or reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ousand
    -0.15
    ↵↵
    -0.15
    ONGL
    -0.15
    ly
    -0.14
    bilt
    -0.14
    lx
    -0.14
    gether
    -0.14
    âĢı
    -0.13
    etter
    -0.13
    line
    -0.13
    POSITIVE LOGITS
    zelf
    0.21
    åĢij
    0.16
    SELF
    0.16
    zzo
    0.16
     sop
    0.16
    ’ve
    0.16
    /us
    0.16
    öyle
    0.15
    ’d
    0.15
    ’ll
    0.15
    Act Density 0.466%

    No Known Activations