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

    Neuronpedia

    INDEX
    Explanations

    phrases related to holding or having control over something

    oai_token-act-pair · gpt-3.5-turbo

    phrases and actions related to holding or grasping

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    γ
    -0.79
    esar
    -0.71
     Pwr
    -0.70
    jc
    -0.66
    Ĥİ
    -0.66
    ²¾
    -0.65
    ĨĴ
    -0.65
    fficient
    -0.65
    nces
    -0.63
    etz
    -0.62
    POSITIVE LOGITS
     hostage
    0.94
     accountable
    0.93
     ransom
    0.88
     veto
    0.87
     scissors
    0.73
    oft
    0.68
     Sabbath
    0.66
     sway
    0.66
     firm
    0.65
    ĸļ
    0.65
    Act Density 0.158%

    No Known Activations