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

    Neuronpedia

    INDEX
    Explanations

    phrases related to centers and focal points in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reau
    -0.19
    abet
    -0.17
    udge
    -0.16
    ÙĪÛĮÙĦ
    -0.15
     sid
    -0.15
    soever
    -0.15
    ùi
    -0.15
     ramp
    -0.14
    sid
    -0.14
    åįĬ
    -0.14
    POSITIVE LOGITS
    -center
    0.20
    ä¸Ń央
    0.17
    央
    0.16
    -cent
    0.16
     centr
    0.16
    central
    0.15
    ushman
    0.15
     surrounded
    0.15
    addListener
    0.15
    zent
    0.15
    Act Density 0.079%

    No Known Activations