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

    Neuronpedia

    INDEX
    Explanations

    phrases related to providing information or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate statements or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lyak
    -0.65
    emic
    -0.65
     obliter
    -0.64
    onga
    -0.63
     manif
    -0.61
    icz
    -0.60
     victory
    -0.60
     criminal
    -0.60
    vation
    -0.59
     decap
    -0.59
    POSITIVE LOGITS
    tumblr
    1.08
    htm
    1.01
     Includes
    1.00
     Specifically
    1.00
     Besides
    0.98
    blogspot
    0.98
     Additionally
    0.97
     Typically
    0.96
     Examples
    0.94
     Especially
    0.93
    Act Density 0.366%

    No Known Activations