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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to the concept of likelihood or potentiality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    o
    -0.20
    hift
    -0.19
    tual
    -0.18
    oÄŁlu
    -0.17
    oen
    -0.17
    oe
    -0.17
    oir
    -0.17
     minded
    -0.17
    isset
    -0.17
    elijke
    -0.17
    POSITIVE LOGITS
    ter
    0.28
    ting
    0.28
    tery
    0.26
    swana
    0.25
    tingham
    0.24
    terdam
    0.24
    ep
    0.20
    tering
    0.19
    TER
    0.19
    teri
    0.19
    Act Density 0.061%

    No Known Activations