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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to perception and cognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abox
    -0.15
    üh
    -0.15
    och
    -0.15
    fee
    -0.14
    ?family
    -0.14
    ož
    -0.14
    ubo
    -0.14
    esh
    -0.14
    anela
    -0.14
    .setDefault
    -0.14
    POSITIVE LOGITS
     Jar
    0.17
    Jar
    0.16
     jar
    0.15
    λμ
    0.14
    bart
    0.14
    .synthetic
    0.14
     mars
    0.14
     itself
    0.14
    algo
    0.14
    hal
    0.13
    Act Density 0.151%

    No Known Activations