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

    Neuronpedia

    INDEX
    Explanations

    phrases related to involvement or participation in activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Slf
    -0.16
     же
    -0.14
    owie
    -0.14
    arcy
    -0.14
    assin
    -0.14
    ãĥ©ãĤ¤ãĥĪ
    -0.13
    anto
    -0.13
    ENSIONS
    -0.13
     ActionTypes
    -0.13
    ian
    -0.13
    POSITIVE LOGITS
    ìĦŃ
    0.18
     Ñģобой
    0.17
     two
    0.15
    MOD
    0.14
    uye
    0.14
    erv
    0.14
    SEA
    0.14
     MOD
    0.13
    uir
    0.13
    uby
    0.13
    Act Density 0.031%

    No Known Activations