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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of removing something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "remove"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.77
     Rate
    -0.76
    zag
    -0.70
    gio
    -0.69
    rium
    -0.69
    ccording
    -0.68
    ortment
    -0.68
    Liter
    -0.67
    externalActionCode
    -0.67
    Act
    -0.67
    POSITIVE LOGITS
    oval
    0.84
     foreskin
    0.78
    cliffe
    0.77
     aback
    0.76
     shaving
    0.76
     explosives
    0.71
     removing
    0.71
     limbs
    0.71
     obsolete
    0.70
    ment
    0.70
    Act Density 0.011%

    No Known Activations