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

    Neuronpedia

    INDEX
    Explanations

    phrases related to effectiveness and measurable outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Selenium
    -0.15
    uge
    -0.15
     Zus
    -0.15
     teb
    -0.15
    orelease
    -0.15
    gv
    -0.15
    igli
    -0.14
    variants
    -0.14
    ajaran
    -0.14
    impan
    -0.14
    POSITIVE LOGITS
    éijij
    0.15
     hours
    0.15
    Uniform
    0.15
    recur
    0.15
    ÑĤÑĮ
    0.14
     Uns
    0.14
    angen
    0.14
     Uniform
    0.14
     BASIC
    0.14
     catalog
    0.13
    Act Density 0.020%

    No Known Activations