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

    Neuronpedia

    INDEX
    Explanations

    concepts related to mental processes and states of mind

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scherer
    -0.79
    utscher
    -0.78
     Schröder
    -0.77
    allenges
    -0.73
     Walsh
    -0.73
    ecutable
    -0.72
    zieher
    -0.71
     Rosenberg
    -0.70
    crumbs
    -0.70
    parate
    -0.68
    POSITIVE LOGITS
     MIND
    1.76
     Mind
    1.61
    MIND
    1.56
     mind
    1.49
    mind
    1.47
     minds
    1.41
    Mind
    1.40
     Mindy
    1.21
     Minds
    1.20
    minds
    1.05
    Act Density 0.047%

    No Known Activations