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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing considerations or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    topics related to technology and innovation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.68
     Syndrome
    -0.58
    ?".
    -0.56
     selves
    -0.55
     cape
    -0.55
     hating
    -0.54
     Bahamas
    -0.52
     kisses
    -0.52
    ses
    -0.52
     Indies
    -0.51
    POSITIVE LOGITS
    yrinth
    0.84
    actionDate
    0.69
    atform
    0.66
     remarkably
    0.65
    undown
    0.64
    undrum
    0.62
     strikingly
    0.62
    olin
    0.61
     exactly
    0.60
     controversial
    0.60
    Act Density 0.832%

    No Known Activations