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

    Neuronpedia

    INDEX
    Explanations

    words related to decision-making or action

    oai_token-act-pair · gpt-3.5-turbo

    imperative verbs that indicate necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.66
    catentry
    -0.65
     Holo
    -0.64
    ¥µ
    -0.64
     guiActiveUnfocused
    -0.61
    hire
    -0.61
    pour
    -0.60
    pie
    -0.59
     Latter
    -0.58
    alde
    -0.58
    POSITIVE LOGITS
    escription
    0.84
     urgently
    0.75
     oneself
    0.73
    igate
    0.72
     manually
    0.72
     sacrific
    0.71
     ASAP
    0.67
    dress
    0.64
     backup
    0.62
    ENGTH
    0.61
    Act Density 0.282%

    No Known Activations