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

    Neuronpedia

    INDEX
    Explanations

    statements related to goals and intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to purpose and intention of actions or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dating
    -0.73
    Guard
    -0.72
    fax
    -0.65
    yes
    -0.62
    rock
    -0.61
     preferring
    -0.60
     Latest
    -0.59
    Plus
    -0.59
    Tonight
    -0.59
    numbered
    -0.58
    POSITIVE LOGITS
     awareness
    0.90
    atform
    0.82
    uate
    0.79
    imize
    0.79
    igate
    0.71
    ateurs
    0.70
     perceptions
    0.69
    uction
    0.67
     morale
    0.67
    IENT
    0.67
    Act Density 0.417%

    No Known Activations