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

    Neuronpedia

    INDEX
    Explanations

    expressions related to providing additional information or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nees
    -0.15
    illas
    -0.14
     innocent
    -0.13
     invent
    -0.13
    ometers
    -0.13
     alloc
    -0.13
    .hm
    -0.13
     Martins
    -0.12
    ideos
    -0.12
     myself
    -0.12
    POSITIVE LOGITS
    ilden
    0.17
    unal
    0.17
    .Undef
    0.16
    oven
    0.15
    utsch
    0.15
    yz
    0.15
     RedirectTo
    0.14
    rig
    0.14
    leston
    0.14
    _DEPRECATED
    0.14
    Act Density 0.030%

    No Known Activations