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

    Neuronpedia

    INDEX
    Explanations

    phrases related to counteractions or opposition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to counter-revolutionary and counter-terrorism activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Limits
    -0.66
     Masquerade
    -0.65
    ©¶æ¥µ
    -0.65
     Timber
    -0.63
     Dreams
    -0.62
     Prosper
    -0.61
     Vide
    -0.61
    erest
    -0.60
    é¾įå
    -0.59
     livest
    -0.59
    POSITIVE LOGITS
    ctive
    0.78
    measures
    0.77
    dict
    0.76
    rad
    0.74
    argument
    0.72
    intuitive
    0.72
    counter
    0.72
    ruption
    0.72
    attack
    0.67
    terrorism
    0.66
    Act Density 0.047%

    No Known Activations