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

    Neuronpedia

    INDEX
    Explanations

    terms related to social interaction and engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enko
    -0.16
    ehler
    -0.15
    vens
    -0.15
    erts
    -0.15
    ervas
    -0.15
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.15
    lehem
    -0.14
    .gs
    -0.14
    енко
    -0.14
    bk
    -0.14
    POSITIVE LOGITS
    ãĥ¼ãĥĢ
    0.17
    æĹħ
    0.16
     pro
    0.16
     Hack
    0.15
    ô
    0.15
    .scalablytyped
    0.15
    åĨ°
    0.15
     Mand
    0.15
    kus
    0.14
    yg
    0.14
    Act Density 0.005%

    No Known Activations