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

    Neuronpedia

    INDEX
    Explanations

    references to hooks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Fcn
    -0.65
    jstor
    -0.60
    awt
    -0.56
    ORCID
    -0.56
     néglig
    -0.55
    łaś
    -0.55
     Idol
    -0.52
    PreferredItem
    -0.51
    ukkah
    -0.51
    CreateInfo
    -0.50
    POSITIVE LOGITS
    Cu
    1.33
     cu
    1.27
     Cu
    1.25
     hook
    1.09
     Hook
    1.06
    cu
    0.98
     hooks
    0.97
    hook
    0.97
    Hook
    0.94
     hooking
    0.92
    Act Density 0.103%

    No Known Activations