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

    Neuronpedia

    INDEX
    Explanations

    phrases related to alignment and coordination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yle
    -0.15
    zk
    -0.15
    -widgets
    -0.14
    OPTIONS
    -0.14
    ous
    -0.14
    usher
    -0.14
    ias
    -0.14
    érc
    -0.14
    usal
    -0.14
    imizer
    -0.14
    POSITIVE LOGITS
    ally
    0.23
    ments
    0.18
     towards
    0.16
     Towers
    0.15
    ìŀ¡
    0.15
    amak
    0.15
     ìŀ¡
    0.15
    trinsic
    0.15
    atura
    0.14
     toward
    0.14
    Act Density 0.031%

    No Known Activations