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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various influencing factors or causes

    oai_token-act-pair · gpt-3.5-turbo

    references to various factors influencing a situation or outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alach
    -0.83
    ©¶æ¥µ
    -0.82
     Parables
    -0.75
    gem
    -0.73
    ©¶æ
    -0.72
    phis
    -0.71
    oÄŁ
    -0.69
    ÄŁ
    -0.68
    rito
    -0.68
    BUG
    -0.65
    POSITIVE LOGITS
     factors
    1.14
     Factors
    0.93
    factor
    0.91
     factor
    0.88
     determines
    0.75
     influencing
    0.75
     variables
    0.74
     influences
    0.73
     mitigating
    0.73
     affecting
    0.73
    Act Density 0.013%

    No Known Activations