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

    Neuronpedia

    INDEX
    Explanations

    words related to consequences or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ping
    -0.15
     lòng
    -0.15
    ÑģÑĤан
    -0.15
    eln
    -0.14
    boro
    -0.14
     Rebels
    -0.14
     Preparation
    -0.14
    ahan
    -0.14
    epam
    -0.14
    cep
    -0.14
    POSITIVE LOGITS
     ens
    0.20
    aptured
    0.19
     Powell
    0.16
     entr
    0.16
     sn
    0.16
    üst
    0.16
    eb
    0.15
     enr
    0.15
    kind
    0.15
     Cout
    0.15
    Act Density 0.027%

    No Known Activations