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

    Neuronpedia

    INDEX
    Explanations

    pronouns ('we', 'us', 'our') along with suggestions or directives

    oai_token-act-pair · gpt-3.5-turbo

    references to collective or group actions and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     è£ıè
    -0.74
    ãĤ´ãĥ³
    -0.71
    DAY
    -0.71
     è£ıè¦ļéĨĴ
    -0.68
    REDACTED
    -0.67
    ¿½
    -0.64
     Verge
    -0.62
     practition
    -0.60
    WARE
    -0.60
    ForgeModLoader
    -0.58
    POSITIVE LOGITS
    're
    1.63
    've
    1.40
     gotta
    1.14
    'll
    1.07
     haven
    1.06
     wanna
    1.04
     don
    1.04
     want
    0.99
     kind
    0.95
     have
    0.93
    Act Density 0.264%

    No Known Activations