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

    Neuronpedia

    INDEX
    Explanations

    concepts related to morale and self-esteem

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apor
    -0.78
    vid
    -0.73
    cart
    -0.67
    uran
    -0.66
    erer
    -0.64
    rees
    -0.63
    sighted
    -0.63
    Interstitial
    -0.63
    angler
    -0.63
     Kepler
    -0.63
    POSITIVE LOGITS
     morale
    1.11
     assurance
    0.83
     incre
    0.82
     cohesion
    0.79
     boosters
    0.79
     enh
    0.77
    ilitary
    0.76
     veter
    0.74
    Reviewer
    0.74
     boosting
    0.73
    Act Density 0.013%

    No Known Activations