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

    Neuronpedia

    INDEX
    Explanations

    commands related to gathering information or directing attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Los
    -0.61
    venge
    -0.60
    DM
    -0.60
    KT
    -0.58
    calling
    -0.55
    ocally
    -0.55
    UID
    -0.55
    Sov
    -0.55
     forc
    -0.54
    sonian
    -0.54
    POSITIVE LOGITS
     browse
    0.89
     scrolling
    0.87
     scroll
    0.84
     zoom
    0.83
     CLICK
    0.82
     glimpse
    0.80
     enlarge
    0.79
     explore
    0.78
     yourself
    0.78
     bask
    0.78
    Act Density 0.108%

    No Known Activations