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

    Neuronpedia

    INDEX
    Explanations

    words related to problem-solving

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to problem-solving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    treated
    -0.77
    umption
    -0.70
    acid
    -0.69
    ardy
    -0.69
    irl
    -0.69
    oths
    -0.69
    icipated
    -0.68
    akening
    -0.67
    listed
    -0.67
    eners
    -0.66
    POSITIVE LOGITS
     solve
    1.00
     solving
    0.87
    ĵĺ
    0.87
     Puzzles
    0.82
     Mysteries
    0.79
    vable
    0.78
     puzzles
    0.77
     solves
    0.74
    æ©
    0.72
    ahime
    0.72
    Act Density 0.021%

    No Known Activations