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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the existence of an undefined or general idea or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.17
    tes
    -0.16
    us
    -0.15
     Aim
    -0.15
     ones
    -0.14
    ibrate
    -0.14
    sed
    -0.14
    ongo
    -0.14
     stom
    -0.14
    stant
    -0.14
    POSITIVE LOGITS
     else
    0.26
    else
    0.20
    _else
    0.19
    Else
    0.19
    errat
    0.16
    OffsetTable
    0.15
     Else
    0.15
    ammers
    0.15
    ummy
    0.15
    ALSE
    0.14
    Act Density 0.036%

    No Known Activations