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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating personal feelings and self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.97
    iq
    -0.66
    icals
    -0.64
    iaries
    -0.64
    mons
    -0.63
    APH
    -0.63
    ewitness
    -0.63
    grave
    -0.62
    ãĥīãĥ©
    -0.61
    stros
    -0.59
    POSITIVE LOGITS
     underest
    0.86
     misunder
    0.79
     underestimated
    0.78
     sensing
    0.78
     kinda
    0.76
     luck
    0.74
     overest
    0.74
     somew
    0.73
     forg
    0.72
     depends
    0.71
    Act Density 0.038%

    No Known Activations