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

    Neuronpedia

    INDEX
    Explanations

    words related to investigation or examination

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    orb
    -0.63
    ä¹
    -0.61
    Cele
    -0.60
    CENT
    -0.59
    theless
    -0.58
    MQ
    -0.57
     restraining
    -0.56
    learning
    -0.55
    SPONSORED
    -0.55
     Osw
    -0.55
    POSITIVE LOGITS
    ahead
    0.95
     suspic
    0.84
    ãĤ¶
    0.76
     favorably
    0.74
     alike
    0.74
     forward
    0.73
     backward
    0.69
    ared
    0.68
     into
    0.67
    ocene
    0.66
    Act Density 0.912%

    No Known Activations