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

    Neuronpedia

    INDEX
    Explanations

    phrases related to letting go or putting aside something

    oai_token-act-pair · gpt-3.5-turbo

    expressions that indicate letting go or putting aside

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amen
    -0.81
    Solution
    -0.74
    Response
    -0.71
    CVE
    -0.70
    CLASSIFIED
    -0.69
    ESE
    -0.69
    iov
    -0.69
    uin
    -0.68
    FORMATION
    -0.67
    Stre
    -0.66
    POSITIVE LOGITS
     altogether
    1.15
     inhib
    1.00
     entirely
    0.99
     precon
    0.84
     superflu
    0.80
     pesky
    0.78
     regrets
    0.74
     whining
    0.73
     outright
    0.73
     reliance
    0.73
    Act Density 0.356%

    No Known Activations