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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various aspects of impact or influence

    oai_token-act-pair · gpt-3.5-turbo

    references to economic concepts and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NESS
    -0.81
    cakes
    -0.79
    bolt
    -0.74
    bis
    -0.69
    lins
    -0.65
     Posts
    -0.65
    Train
    -0.65
    Ħ¢
    -0.64
    lass
    -0.64
    ATS
    -0.63
    POSITIVE LOGITS
     tendency
    0.88
     precedence
    0.88
     credibility
    0.84
     reperc
    0.83
     knack
    0.83
     resonance
    0.82
     effect
    0.81
    notations
    0.80
     chance
    0.80
     ripple
    0.80
    Act Density 0.285%

    No Known Activations