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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scams and deception

    oai_token-act-pair · gpt-3.5-turbo

    words related to scams or deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lapse
    -0.73
     neoc
    -0.70
    theless
    -0.70
     reckoning
    -0.70
     reliance
    -0.66
     abundantly
    -0.65
     Ramadan
    -0.63
     foremost
    -0.63
     glor
    -0.62
    araoh
    -0.62
    POSITIVE LOGITS
    cheon
    0.95
    udo
    0.79
    uli
    0.75
    anon
    0.75
    arios
    0.73
    hett
    0.73
    berus
    0.70
    ombat
    0.70
    lear
    0.68
    onica
    0.68
    Act Density 0.103%

    No Known Activations