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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making or taking action

    oai_token-act-pair · gpt-3.5-turbo

    patterns of conditional statements and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gross
    -0.75
    çĶ°
    -0.68
    uca
    -0.68
    ritz
    -0.67
    aido
    -0.66
    Rap
    -0.66
    acts
    -0.65
    Rot
    -0.64
    ollo
    -0.63
    uga
    -0.62
    POSITIVE LOGITS
     mentality
    0.85
     syndrome
    0.82
     attitude
    0.77
     salesman
    0.74
    erness
    0.69
    lihood
    0.67
    -'
    0.67
     trope
    0.66
     sequel
    0.66
     ratio
    0.66
    Act Density 0.178%

    No Known Activations