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

    Neuronpedia

    INDEX
    Explanations

    terms related to potential or possibility

    oai_token-act-pair · gpt-3.5-turbo

    terms related to potential threats and challenges in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     circ
    -0.66
     sadly
    -0.65
    inately
    -0.61
     generally
    -0.60
     frankly
    -0.58
     reins
    -0.58
    Reviewed
    -0.56
     visibly
    -0.56
    gio
    -0.56
     Lonely
    -0.55
    POSITIVE LOGITS
    ãĥŃ
    0.79
    ãĤ¿
    0.76
    arenthood
    0.72
    ãĥīãĥ©
    0.71
    ãĥķãĤ©
    0.70
    ãĥĥãĤ¯
    0.69
    ãĥĥãĥĪ
    0.69
    SpaceEngineers
    0.68
    ãĤ¤ãĥĪ
    0.67
    ãĥ¤
    0.67
    Act Density 0.356%

    No Known Activations