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

    Neuronpedia

    INDEX
    Explanations

    phrases related to setting something aside or putting it on hold

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    putting things aside

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    хьтан
    -0.75
    Viited
    -0.56
    BagConstraints
    -0.51
     argint
    -0.51
     lenker
    -0.50
    AnimationsModule
    -0.49
    oa̍t
    -0.49
    protoimpl
    -0.48
     autorytatywna
    -0.47
    UserScript
    -0.44
    POSITIVE LOGITS
     aside
    0.85
     sidelined
    0.74
    iseite
    0.69
    aside
    0.69
     sideline
    0.68
     Aside
    0.65
     apart
    0.63
    Aside
    0.60
     aparte
    0.59
     sidelines
    0.59
    Act Density 0.022%

    No Known Activations