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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate positive actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aking
    -0.16
     Ashe
    -0.15
    akes
    -0.15
    .mit
    -0.15
    ect
    -0.15
    rer
    -0.15
    thouse
    -0.14
     Ãĸn
    -0.14
    t
    -0.14
    inel
    -0.14
    POSITIVE LOGITS
    URN
    0.16
    itarian
    0.16
    ruk
    0.15
     Nic
    0.15
    ابÛĮ
    0.14
    ähr
    0.14
     Decompiled
    0.14
    assy
    0.14
     Dow
    0.14
     Griffith
    0.14
    Act Density 0.089%

    No Known Activations