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

    Neuronpedia

    INDEX
    Explanations

    contractions indicating possession or ongoing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rb
    -0.16
    owns
    -0.16
    uada
    -0.15
    ãĤŃãĥ¼
    -0.14
    мÑĥ
    -0.14
    ANTA
    -0.14
    ais
    -0.14
    sj
    -0.14
    oggler
    -0.14
    eld
    -0.13
    POSITIVE LOGITS
    ATUS
    0.14
    .resolution
    0.14
    _FW
    0.14
     RTS
    0.14
     extra
    0.14
    çIJĥ
    0.13
     unlucky
    0.13
     FW
    0.13
     AAA
    0.13
     Ful
    0.13
    Act Density 0.222%

    No Known Activations