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

    Neuronpedia

    INDEX
    Explanations

    concepts related to freedom or the state of being free

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oscope
    -0.74
     Saban
    -0.73
     Bog
    -0.66
     Eug
    -0.63
    need
    -0.63
    ents
    -0.62
    ENTS
    -0.62
     Ange
    -0.62
    amel
    -0.62
     Tie
    -0.61
    POSITIVE LOGITS
     roam
    0.85
    bies
    0.85
    boot
    0.84
     spirited
    0.73
    zing
    0.72
    born
    0.71
     indemn
    0.71
    icient
    0.70
    bern
    0.70
    zes
    0.70
    Act Density 0.014%

    No Known Activations