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

    Neuronpedia

    INDEX
    Explanations

    words associated with collaborative roles and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lian
    -0.16
    ulin
    -0.15
    Ïģιν
    -0.15
    /ph
    -0.14
    li
    -0.14
    igg
    -0.14
    /tasks
    -0.14
    ÏĦο
    -0.13
    uggle
    -0.13
    urtles
    -0.13
    POSITIVE LOGITS
     co
    0.18
    imetype
    0.14
    LTR
    0.14
    argout
    0.14
     Lub
    0.14
     vere
    0.14
     vie
    0.14
    HEMA
    0.14
     with
    0.13
     invent
    0.13
    Act Density 0.020%

    No Known Activations