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

    Neuronpedia

    INDEX
    Explanations

    concepts related to measurements and evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uisse
    -0.17
    ãĤĪãģĨãģ§ãģĻ
    -0.15
    aber
    -0.15
    ount
    -0.14
    Getter
    -0.14
     SAF
    -0.14
    åĭ¤
    -0.13
    esser
    -0.13
    842
    -0.13
     زاد
    -0.13
    POSITIVE LOGITS
    μεÏģο
    0.16
    ais
    0.15
    ambda
    0.15
    sing
    0.15
    NAMESPACE
    0.14
    ilo
    0.14
     scatter
    0.14
    MAND
    0.14
     pal
    0.14
    sla
    0.14
    Act Density 0.015%

    No Known Activations