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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating proximity or closeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eger
    -0.15
    undry
    -0.15
    yw
    -0.15
    oding
    -0.14
     неÑģ
    -0.14
    VERR
    -0.14
    reen
    -0.14
    IAL
    -0.14
    ode
    -0.14
    jug
    -0.14
    POSITIVE LOGITS
     being
    0.19
     reality
    0.17
    nero
    0.17
     zero
    0.16
     shore
    0.14
    icrosoft
    0.14
     saying
    0.14
    shore
    0.14
     ideal
    0.14
     what
    0.14
    Act Density 0.040%

    No Known Activations