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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the effects or impacts of actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to effects or implications of actions or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    §
    -0.69
    Ancient
    -0.64
    achus
    -0.63
    £ı
    -0.62
     Ded
    -0.61
    eon
    -0.61
    ctuary
    -0.61
    stretched
    -0.61
    acus
    -0.61
     manually
    -0.59
    POSITIVE LOGITS
     impact
    1.56
     effect
    1.53
     effects
    1.44
     impacts
    1.42
    effect
    1.34
     consequences
    1.33
    effects
    1.32
     repercussions
    1.32
     effectiveness
    1.30
    impact
    1.29
    Act Density 0.729%

    No Known Activations