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

    Neuronpedia

    INDEX
    Explanations

    terms related to targeted groups and their roles or interests within specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ohn
    -0.16
    .dds
    -0.15
    taÅŁ
    -0.14
    VISIBLE
    -0.14
    voir
    -0.14
    说è¯Ŀ
    -0.14
    ůst
    -0.14
     koc
    -0.13
    ilage
    -0.13
    pty
    -0.13
    POSITIVE LOGITS
     looking
    0.49
    looking
    0.42
     Looking
    0.36
    Looking
    0.35
    -looking
    0.33
     alike
    0.33
     wanting
    0.32
     interested
    0.29
     LOOK
    0.28
     interes
    0.27
    Act Density 0.213%

    No Known Activations