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

    Neuronpedia

    INDEX
    Explanations

    phrases related to restraint or delay

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to restraint or holding back

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ²¾
    -0.74
    ashtra
    -0.73
    aundering
    -0.73
    ersen
    -0.72
    £ı
    -0.68
    Sport
    -0.68
    ivia
    -0.67
    ceivable
    -0.66
    swick
    -0.66
    olkien
    -0.65
    POSITIVE LOGITS
     ransom
    0.91
     reins
    0.80
     tight
    0.76
    hold
    0.71
     hostage
    0.67
     firm
    0.65
     sway
    0.65
     hold
    0.64
     veto
    0.64
    posts
    0.62
    Act Density 0.060%

    No Known Activations