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

    Neuronpedia

    INDEX
    Explanations

    references to individuals presenting information or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.51
    อ้าง
    -0.49
     للمعارف
    -0.49
    setAccessible
    -0.48
     Signalez
    -0.47
    letic
    -0.44
    Parms
    -0.44
     ERSITY
    -0.43
    toThrow
    -0.43
    juris
    -0.43
    POSITIVE LOGITS
     invasion
    0.85
     speaker
    0.80
     invading
    0.78
     invaded
    0.74
     invasions
    0.73
    Speaker
    0.72
     speakers
    0.70
     invade
    0.69
     Invasion
    0.69
     Speaker
    0.67
    Act Density 0.074%

    No Known Activations