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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate examination or observation of data or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ings
    -0.20
    /remove
    -0.17
    sv
    -0.16
    ucene
    -0.16
    /disable
    -0.16
    /write
    -0.15
    ıb
    -0.15
    ighth
    -0.14
    oad
    -0.14
    idal
    -0.14
    POSITIVE LOGITS
    redient
    0.23
    redients
    0.22
    /testing
    0.20
    ly
    0.19
    gg
    0.19
    /loading
    0.19
    tour
    0.17
    wi
    0.17
     oneself
    0.16
    REDIENT
    0.16
    Act Density 0.117%

    No Known Activations