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

    Neuronpedia

    INDEX
    Explanations

    reflections on thoughts and mental processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dna
    -0.15
    velt
    -0.15
    ãĥ³ãĥij
    -0.15
    ¬¬
    -0.14
    drs
    -0.14
    ulence
    -0.14
    mgr
    -0.14
    ieri
    -0.14
    身
    -0.13
    aneous
    -0.13
    POSITIVE LOGITS
     minds
    0.68
     mind
    0.68
     Mind
    0.56
     Minds
    0.56
    mind
    0.54
    Mind
    0.52
     brain
    0.42
     mente
    0.42
     minded
    0.42
    èĦij
    0.38
    Act Density 0.193%

    No Known Activations