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

    Neuronpedia

    INDEX
    Explanations

    terms related to inner experiences and introspection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sse
    -0.17
    sdale
    -0.16
    sin
    -0.16
    entifier
    -0.16
    adam
    -0.16
    åħ¥ãĤĬ
    -0.16
    iec
    -0.16
    ละ
    -0.15
    amel
    -0.15
    /***/
    -0.15
    POSITIVE LOGITS
    most
    0.52
    halb
    0.37
    MOST
    0.29
    -most
    0.29
     most
    0.28
     workings
    0.27
    /ext
    0.25
    wear
    0.25
    -city
    0.23
    Most
    0.23
    Act Density 0.020%

    No Known Activations