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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relational or directional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.22
    /INFO
    -0.16
    uae
    -0.15
    AppBundle
    -0.15
    ksam
    -0.14
    جÙĪ
    -0.14
    klä
    -0.14
    828
    -0.14
    832
    -0.13
    ège
    -0.13
    POSITIVE LOGITS
    gether
    0.32
    atre
    0.24
    ersen
    0.20
    ir
    0.20
    clusive
    0.19
    xic
    0.19
    oret
    0.18
    ilet
    0.18
    oner
    0.18
    asted
    0.17
    Act Density 0.050%

    No Known Activations