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

    Neuronpedia

    INDEX
    Explanations

    the presence of directional or motivational phrases that indicate looking towards or seeking something

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

    look to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     méret
    -0.43
    DebuggerStep
    -0.35
    Спољашње
    -0.35
     declaração
    -0.35
     ért
    -0.34
    ctrica
    -0.34
     exquisitely
    -0.34
     dégustation
    -0.34
    avascript
    -0.34
    switch
    -0.33
    POSITIVE LOGITS
    verwijspagina
    0.63
     '\\;'
    0.57
     Numerade
    0.57
     $_[
    0.56
    adpleegd
    0.55
     ब्रेकडाउन
    0.54
    ⓧ
    0.54
    antMatchers
    0.52
    waitKey
    0.51
     OMITBAD
    0.51
    Act Density 0.050%

    No Known Activations