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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve the action of checking or looking at something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iste
    -0.19
    nie
    -0.17
     barr
    -0.16
    ByKey
    -0.15
     solic
    -0.15
    igs
    -0.15
    oker
    -0.14
    ux
    -0.14
    ular
    -0.14
    owitz
    -0.14
    POSITIVE LOGITS
    msgid
    0.17
    taj
    0.16
    tae
    0.16
    idl
    0.15
    иÑĢÑĥ
    0.14
    .cgi
    0.13
    esini
    0.13
    amba
    0.13
    alon
    0.13
     Yus
    0.13
    Act Density 0.022%

    No Known Activations